Tootfinder

InterGSEdit: Interactive 3D Gaussian Splatting Editing with 3D Geometry-Consistent Attention Prior
Minghao Wen, Shengjie Wu, Kangkan Wang, Dong Liang
https://arxiv.org/abs/2507.04961

InterGSEdit: Interactive 3D Gaussian Splatting Editing with 3D Geometry-Consistent Attention Prior
3D Gaussian Splatting based 3D editing has demonstrated impressive performance in recent years. However, the multi-view editing often exhibits significant local inconsistency, especially in areas of non-rigid deformation, which lead to local artifacts, texture blurring, or semantic variations in edited 3D scenes. We also found that the existing editing methods, which rely entirely on text prompts make the editing process a "one-shot deal", making it difficult for users to control the editing de…

The best microcontroller thing I did last year was build this little kit that fits in a 3D printed rugged box and covers close to 90% of things I need to deal with for the products I sell & support.
I can easily throw it in my bag when I'm on the road, otherwise it sits on my desk where I can quickly grab it to test something.
#maker

#Requiescat For Bill Atkinson. https://www.youtube.com/watch?v=pZ_SJnZfF7g&pp=ygUTYXBwbGUgQmlsbCBBdGtpbnNvbg==

Fraunhofer IOF: 3D-Erkennung transparenter Objekte in weniger als 1,5 Sekunden
Die automatische Erkennung von 3D-Objekten mit "unkooperativen" Oberflächen ist eine schwierige und langsame Angelegenheit. Das Fraunhofer IOF hat eine Lösung.

Near-Field Codebook-Based 3D Spherical Channel Estimation for UCA XL-MIMO Systems
Chenliang Yang, Guangchi Zhang, Miao Cui, Qingqing Wu, Yong Zeng
https://arxiv.org/abs/2507.03507

Near-Field Codebook-Based 3D Spherical Channel Estimation for UCA XL-MIMO Systems
Extremely large-scale multiple input multiple output (XL-MIMO), a key technology for 6G communications, faces challenges in near-field channel estimation due to spherical wavefronts and the need for three-dimensional (3D) spatial characterization, particularly with uniform circular arrays (UCAs). This letter proposes a spherical-domain simultaneous orthogonal matching pursuit (S-SOMP) based scheme tailored for near-field 3D channel estimation in UCA-equipped XL-MIMO systems. We establish a spar…

3D PixBrush: Image-Guided Local Texture Synthesis
Dale Decatur, Itai Lang, Kfir Aberman, Rana Hanocka
https://arxiv.org/abs/2507.03731 https://

3D PixBrush: Image-Guided Local Texture Synthesis
We present 3D PixBrush, a method for performing image-driven edits of local regions on 3D meshes. 3D PixBrush predicts a localization mask and a synthesized texture that faithfully portray the object in the reference image. Our predicted localizations are both globally coherent and locally precise. Globally - our method contextualizes the object in the reference image and automatically positions it onto the input mesh. Locally - our method produces masks that conform to the geometry of the refe…

In #Selsingen entsteht Norddeutschlands erstes #Bürogebäude mit 3D-Druck-Mauerwerk.
In nur 105 Stunden druckte ein #Portaldrucker die Außenwände. Zwei Fachkräfte steuern den …

Häuser aus dem Drucker: Wie die 3D-Technik die Bauwirtschaft umkrempeln könnte
In nur 105 Stunden entsteht mithilfe eines 3D-Druckers das komplette Mauerwerk eines zweigeschossigen Bürogebäudes. In Norddeutschland ist es das erste Bauprojekt dieser Art.

DragonFly: Single mmWave Radar 3D Localization of Highly Dynamic Tags in GPS-Denied Environments
Skanda Harisha, Jimmy G. D. Hester, Aline Eid
https://arxiv.org/abs/2507.04602

DragonFly: Single mmWave Radar 3D Localization of Highly Dynamic Tags in GPS-Denied Environments
The accurate localization and tracking of dynamic targets, such as equipment, people, vehicles, drones, robots, and the assets that they interact with in GPS-denied indoor environments is critical to enabling safe and efficient operations in the next generation of spatially aware industrial facilities. This paper presents DragonFly , a 3D localization system of highly dynamic backscatter tags using a single MIMO mmWave radar. The system delivers the first demonstration of a mmWave backscatter s…

Classification of monopole deformed 3d $\mathcal{N}=2$ Seiberg-like duality with an adjoint matter
Qiang Jia, Sungjoon Kim
https://arxiv.org/abs/2507.04950

Classification of monopole deformed 3d $\mathcal{N}=2$ Seiberg-like duality with an adjoint matter
We propose a new 3d $\mathcal{N}=2$ Seiberg-like duality of adjoint SQCD(Kim-Park duality) with linear monopole superpotential terms which encompasses known monopole deformed Kim-Park dualities. Equipped with this, we classify all the monopole deformed Kim--Park dualities up to quadratic powers of monopole deformations, and find all are equivalent either to the original Kim--Park, or to the proposed duality. With the recently developed deconfined perspective, this means all the working monopole…

3D tracking of Plankton with single-camera stereoscopy
J. Moscatelli, X Benoit Gonin, F. Elias
https://arxiv.org/abs/2506.05365 https://

3D tracking of Plankton with single-camera stereoscopy
We introduce a device developed to perform a 3D tracking of passive or active particles under flow, confined in a medium of hundreds micrometers wide. Micro-objects are placed inside a vertical glass capillary and two mirrors are set behind it with a certain angle, making it possible to have the two reflections of the capillary on the same optical plane. A 3D reconstruction of the trajectories, captured with a single camera, is carried out along the vertical axis with a micrometer-scale precisi…

Segmentation of separated Lumens in 3D CTA images of Aortic Dissection
Christophe Lohou, Bruno Miguel
https://arxiv.org/abs/2507.03655 https://

Segmentation of separated Lumens in 3D CTA images of Aortic Dissection
Aortic dissection is a serious pathology and requires an emergency management. It is characterized by one or more tears of the intimal wall of the normal blood duct of the aorta (true lumen); the blood under pressure then creates a second blood lumen (false lumen) in the media tissue. The two lumens are separated by an intimal wall, called flap. From the segmentation of connected lumens (more precisely, blood inside lumens) of an aortic dissection 3D Computed Tomography Angiography (CTA) image,…

What else is new? We got a 3D printer! Printed this cassette holder.

Is AI your ghost writer or creative partner? The key is using AI as a collaborator, not a replacement for your authentic voice. I'm finding ways to leverage AI while preserving what makes my perspective unique. How are you navigating this balance in _your_ work? 

Partner, Not Proxy: How I Use AI Without Losing My Voice
When Andrew Winston asked recently, “How do we feel about using AI—trained on our own writing—to help create something new?” I had a lot to say. Let me try to distill a few key points, drawn from how I’m using AI today, that might be helpful to others exploring this new world.

An der @Adolf-Reichwein-Schule in #Marburg lässt ein Deutschlehrer im Unterricht Hiphop-Texte verfassen und ist auch selber als Rapper Mr. Lu bekannt – will aber Lehrer bleiben. Gut, dass es das auch gibt 😊
https://m.yo…

The Beatles - 1964 US Tour Reconstruction - Full Concert (Old Version)
https://www.youtube.com/watch?v=WB2emRflAdU&pp=QAFIAQ==
Na de film kwam YouTube met dit gereconstrueerde concert vsn de Beatles.
Eigenlijk veel lekkerder om naar t…

Modelling the 3D atmospheric structure of the cold Jupiter WD1856 534b orbiting a white dwarf
Pascal A. Noti, Elspeth K. H. Lee, Daniel Kitzmann, Ryan MacDonald, Sydney Jenkins, Arjun Savel, Mary Anne Limbach, Christoph Mordasini
https://arxiv.org/abs/2507.05422

Modelling the 3D atmospheric structure of the cold Jupiter WD1856+534b orbiting a white dwarf
WD-1856b+534b (WD-1856b) is to date the only detected cold Jupiter outside of our Solar System. This cold Jupiter can provide useful information about the cold giants in our Solar System. Recent JWST observations have targeted WD-1856b, with more scheduled in the near future. To support the interpretation of these observations, we simulated WD-1856b using a three-dimensional (3D) General Circulation Model (GCM) and produced synthetic emission spectra of the planet. We used the Exo-FMS GCM with …

Existence of weak solution of 3D ferrohydrodynamic equations with transport noise: Bloch-Torrey regularisation
Aristide Ndongmo Ngana, Paul Razafimandimby
https://arxiv.org/abs/2507.03388

Existence of weak solution of 3D ferrohydrodynamic equations with transport noise: Bloch-Torrey regularisation
In this article, we consider a stochastic ferrohydrodynamic system which describes the Bloch-Torrey regularization of the motion of an electrically conducting ferrofluids driven by transport noise filling a 3D bounded domain with a smooth boundary. We prove the global existence of a probabilistic weak solution of the stochastic system by making use of the combination of Galerkin method and compactness method. The system under study is basically a coupling of the Navier-Stokes equations with int…

Diving into Godot for some personal projects, and getting my 3D pipeline sorted out and man... the Blender to Godot pipeline is so nice. Just being able to straight up save .blend files complete with modifiers and the like and have it work so seamlessly in Godot is just... (chef's kiss)
#Godot #GameDev

SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation
Jiahao Zhu, Zixuan Chen, Guangcong Wang, Xiaohua Xie, Yi Zhou
https://arxiv.org/abs/2507.05256

SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation
Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) to score distillation. However, due to the imbalance between self-consistency and cross-consistency, these CD-based methods inherently suffer from improper conditional guidance, leading to sub-optimal generation results. To address this issue, we present SegmentDreamer, a novel framework designed to fully unleash the p…

Slow progress the last couple days because I've been going into the office for work and the commute is eating up my time I'd otherwise spend on such things.
But now it's the weekend and the switch engine board is coming together nicely.
Still have 514 nets to route - mostly the supervisor, line card management buses, and power supply but also some other odds and ends like the FPGA JTAG and part of the SPI flash.
Also I have to get the tach/PWM signals from the m…

A 3D Machine Learning based Volume Of Fluid scheme without explicit interface reconstruction
Moreno Pintore, Bruno Despr\'es
https://arxiv.org/abs/2507.05218

A 3D Machine Learning based Volume Of Fluid scheme without explicit interface reconstruction
We present a machine-learning based Volume Of Fluid method to simulate multi-material flows on three-dimensional domains. One of the novelties of the method is that the flux fraction is computed by evaluating a previously trained neural network and without explicitly reconstructing any local interface approximating the exact one. The network is trained on a purely synthetic dataset generated by randomly sampling numerous local interfaces and which can be adapted to improve the scheme on less re…

Ich muss sagen, Mapy (https://mapy.com) find ich wirklich eine nette auf OpenStreetMap aufsetzende ~App. Routen planen und finden scheint leicht zu gehen.
Bei Locations (Suche) wird es dann aber schon leider wieder wenig. Wäre cool, wenn einfach alles aus

Elastohydrodynamics of 3D chemically active filaments
Matthew D Butler, Benjamin J Walker, Thomas Montenegro-Johnson, Panayiota Katsamba
https://arxiv.org/abs/2507.03586

Elastohydrodynamics of 3D chemically active filaments
Active deformable filaments exhibit a large range of qualitatively different three-dimensional dynamics, depending on their flexibility, the strength of the active forcing, and the surrounding environment. For a sufficiently strong activity, the resulting forces buckle the filament into different shapes, altering its dynamic behaviour. We investigate the dynamic behaviour of elastic, chemically propelled phoretic filaments, combining two existing models; a local version of slender phoretic theo…

Application of multimodal AI to aid scene perception for the visually impaired https://www.mdpi.com/2076-3417/15/12/6442

🇺🇦 #NowPlaying on #BBC6Music's #MaryAnneHobbs
3D:
🎵 Jupiter
#3D
https://3trianglesrecords.bandcamp.com/album/3d
Please 🔁 BOOST to share what you like
- your followers don't see if you ⭐ favourite a post

Zum Greifen nah: KI-generierte 3D-Umgebungen in VR
World Labs entwickelt eine KI, die interaktive 3D-Umgebungen aus Prompts oder Bildern erzeugt. Mit Geräten wie Meta Quest 3 kann man diese jetzt in 3D erleben.

AI-powered Contextual 3D Environment Generation: A Systematic Review
Miguel Silva, Alexandre Valle de Carvalho
https://arxiv.org/abs/2506.05449 https://

AI-powered Contextual 3D Environment Generation: A Systematic Review
The generation of high-quality 3D environments is crucial for industries such as gaming, virtual reality, and cinema, yet remains resource-intensive due to the reliance on manual processes. This study performs a systematic review of existing generative AI techniques for 3D scene generation, analyzing their characteristics, strengths, limitations, and potential for improvement. By examining state-of-the-art approaches, it presents key challenges such as scene authenticity and the influence of te…

Dictionary-Based Reconstruction of Spatio-Temporal 3D Magnetic Field Images from Quantum Diamond Microscope
Anuj Bathla, Madhur Parashar, Matthew Markham, Ajit Rajwade, Kasturi Saha
https://arxiv.org/abs/2506.05491

Dictionary-Based Reconstruction of Spatio-Temporal 3D Magnetic Field Images from Quantum Diamond Microscope
Three-dimensional magnetic imaging with high spatio-temporal resolution is critical for probing current paths in various systems, from biosensing to microelectronics. Conventional 2D Fourier-based current source localization methods are ill-posed in multilayer or dynamic systems due to signal overlap and noise. In this work, we demonstrate an innovative nitrogen-vacancy (NV) center-based wide-field magnetic microscopy technique for dynamic three-dimensional imaging and localization of current s…

Photonic Origami of Silica on a Silicon Chip with Microresonators and Concave Mirrors
Manya Malhotra, Ronen Ben-Daniel, Fan Cheng, Tal Carmon
https://arxiv.org/abs/2507.04484

Photonic Origami of Silica on a Silicon Chip with Microresonators and Concave Mirrors
3D printing of high-quality silica photonic structures is particularly challenging, as surface roughness at the nanoscale can severely degrade optical performance through scattering losses. Here, we develop a technique to fold ultrasmooth silica on silicon chips into such desired 3D structures. A laser-induced, surface-tension-driven method achieves folding with 20 nm alignment accuracy, enabling origami-like polylines and helices with integrated 0.5 nm-smooth photonic devices. The technique al…

TV: AVRO Column (19870105) - Economie met E Peereboom (Telefoon)
https://www.youtube.com/watch?v=nGBEuHolRP4&t=147s&pp=2AGTAZACAQ==
Benieuwd naar de versie anno 2025..😅
(Via @…

3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
Hongyan Zhi, Peihao Chen, Siyuan Zhou, Yubo Dong, Quanxi Wu, Lei Han, Mingkui Tan
https://arxiv.org/abs/2506.06199

3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
Manipulation has long been a challenging task for robots, while humans can effortlessly perform complex interactions with objects, such as hanging a cup on the mug rack. A key reason is the lack of a large and uniform dataset for teaching robots manipulation skills. Current robot datasets often record robot action in different action spaces within a simple scene. This hinders the robot to learn a unified and robust action representation for different robots within diverse scenes. Observing how …

Coupling 1D stellar evolution with 3D-hydrodynamical simulations on-the-fly III: stellar evolution at different metallicities
Yixiao Zhou, Jakob L. R{\o}rsted, Achim Weiss, Andreas C. S. J{\o}rgensen, Cis Lagae, Luisa F. Rodr\'iguez D\'iaz, Yaguang Li, Mark L. Winther, Jens R. Larsen, J{\o}rgen Christensen-Dalsgaard, Oleg Kochukhov, Karen R. Pollard, Tanda Li

Coupling 1D stellar evolution with 3D-hydrodynamical simulations on-the-fly III: stellar evolution at different metallicities
A major weakness in one-dimensional (1D) stellar structure and evolution modeling is the simplified treatment of convection, which leads to erroneous near-surface stratification and considerable uncertainties in predicted effective temperatures and luminosities of low-mass stars. In a series of preceding works, a novel method for coupling 1D stellar structural models with a grid of 3D surface convection simulations during stellar evolution was developed, at solar metallicity. This 1D-3D couplin…

A 3D Mobile Crowdsensing Framework for Sustainable Urban Digital Twins
Taku Yamazaki (Shibaura Institute of Technology), Kaito Watanabe (Shibaura Institute of Technology), Tatsuya Kase (Shibaura Institute of Technology), Kenta Hasegawa (Shibaura Institute of Technology), Koki Saida (Shibaura Institute of Technology), Takumi Miyoshi (Shibaura Institute of Technology)

A 3D Mobile Crowdsensing Framework for Sustainable Urban Digital Twins
In this article, we propose a 3D mobile crowdsensing (3D-MCS) framework aimed at sustainable urban digital twins (UDTs). The framework comprises four key mechanisms: (1) the 3D-MCS mechanism, consisting of active and passive models; (2) the Geohash-based spatial information management mechanism; (3) the dynamic point cloud integration mechanism for UDTs; and (4) the web-based real-time visualizer for 3D-MCS and UDTs. The active sensing model features a gamified 3D-MCS approach, where participan…

I’m gonna call this one a fail… some lines are too thin, overspray, and the 3D printed stencil warped after using it!

It's like a 3D puzzle. This 18th-century Italian safe has the most unique unlocking sequences ever.

MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation
Yucheng Wang, Dan Xu
https://arxiv.org/abs/2507.05092

MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation
Audio-driven talking head generation is critical for applications such as virtual assistants, video games, and films, where natural lip movements are essential. Despite progress in this field, challenges remain in producing both consistent and realistic facial animations. Existing methods, often based on GANs or UNet-based diffusion models, face three major limitations: (i) temporal jittering caused by weak temporal constraints, resulting in frame inconsistencies; (ii) identity drift due to ins…

ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting
Daniel Wang, Patrick Rim, Tian Tian, Alex Wong, Ganesh Sundaramoorthi
https://arxiv.org/abs/2506.05480

ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting
We present ODE-GS, a novel method that unifies 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs) to forecast dynamic 3D scenes far beyond the time span seen during training. Existing neural rendering systems - whether NeRF- or 3DGS-based - embed time directly in a deformation network and therefore excel at interpolation but collapse when asked to predict the future, where timestamps are strictly out-of-distribution. ODE-GS eliminates this dependency: after learning…

Caroline van der Plas leed een mestnederlaag in Brussel – maar doet alsof alles nog mogelijk is
https://www.ftm.nl/art…

Caroline van der Plas leed een mestnederlaag in Brussel – maar doet alsof alles nog mogelijk is
Minister van Landbouw Femke Wiersma wil in Brussel wéér gaan vragen om een uitzondering op de Europese mestregels. Follow the Money vroeg de verslagen op van eerdere gesprekken die zij, haar topambtenaren en Caroline van der Plas daarover voerden. De conclusie: Wiersma’s plan heeft geen schijn van kans.

Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy
Yu Feng, Weikai Lin, Yuge Cheng, Zihan Liu, Jingwen Leng, Minyi Guo, Chen Chen, Shixuan Sun, Yuhao Zhu
https://arxiv.org/abs/2506.05682

Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy
3D Gaussian Splatting (3DGS) has vastly advanced the pace of neural rendering, but it remains computationally demanding on today's mobile SoCs. To address this challenge, we propose Lumina, a hardware-algorithm co-designed system, which integrates two principal optimizations: a novel algorithm, S^2, and a radiance caching mechanism, RC, to improve the efficiency of neural rendering. S2 algorithm exploits temporal coherence in rendering to reduce the computational overhead, while RC leverages th…

3D-Druck: Spezielles Resin kombiniert feste und softe Materialeigenschaften
Ein einzelnes Druckharz kann beim Druck mit dem 3D-Drucker entweder weiche oder harte Eigenschaften annehmen. Dafür ist ein spezielles Druckverfahren nötig.

Evidence of haze control of Pluto’s atmospheric heat balance from JWST/MIRI thermal light curves: #Pluto

Incompressible limit for the 3D compressible FENE dumbbell model
Jincheng Gao, Jiahong Wu, Zheng-an Yao, Ruijia Yu
https://arxiv.org/abs/2507.03533 https:/…

Incompressible limit for the 3D compressible FENE dumbbell model
In this work, we study the global-in-time incompressible limit of the compressible FENE dumbbell model on the three-dimensional torus T^3, where the incompressible limit is driven by large volume viscosity. To establish this limit, we develop time-weighted a priori estimates that yield decay rates for strong solutions. A key challenge arises from the fact that increasing the volume viscosity suppresses the decay of high-frequency components, thereby weakening the dissipation of the density and …

Decremental Greedy Polygons and Polyhedra Without Sharp Angles
David Eppstein
https://arxiv.org/abs/2507.04538 https://arxiv.org/pdf/…

Decremental Greedy Polygons and Polyhedra Without Sharp Angles
We show that the max-min-angle polygon in a planar point set can be found in time $O(n\log n)$ and a max-min-solid-angle convex polyhedron in a three-dimensional point set can be found in time $O(n^2)$. We also study the maxmin-angle polygonal curve in 3d, which we show to be $\mathsf{NP}$-hard to find if repetitions are forbidden but can be found in near-cubic time if repeated vertices or line segments are allowed, by reducing the problem to finding a bottleneck cycle in a graph. We formalize …

Exploiting complex 3D-printed surface structures for portable quantum technologies
Nathan Cooper, David Johnson, Benjamin Hopton, Matthew Overton, David Stupple, Alexandra Bratu, Edward Wilson, John Robinson, Laurence Coles, Manolis Papastavrou, Lucia Hackermueller
https://arxiv.org/abs/2507.01476

Exploiting complex 3D-printed surface structures for portable quantum technologies
Portable quantum technologies require robust, lightweight apparatus with superior performance. For techniques dependent upon high-vacuum environments, such as atom interferometers and atomic clocks, 3D-printing enables new avenues to tailor in-vacuum gas propagation dynamics. We demonstrate intricate, fine-scale surface patterning of 3D-printed vacuum components to increase the rate at which gas particles collide with the surface. By applying a non-evaporable getter coating for use as a surface…

Speculative Evolution Through 3D Cellular Automata
Amir Hossein Khazaei
https://arxiv.org/abs/2505.01692 https://arxiv.org/pdf/2505.0…

Speculative Evolution Through 3D Cellular Automata
This project explores speculative evolution through a 3D implementation of Conway's Game of Life, using procedural simulation to generate unfamiliar extraterrestrial organic forms. By applying a volumetric optimized workflow, the raw cellular structures are smoothed into unified, bone-like geometries that resemble hypothetical non-terrestrial morphologies. The resulting forms, strange yet organic, are 3D printed as fossil-like artifacts, presenting a tangible representation of generative struct…

The EoR 21-cm Bispectrum at $z=8.2$ from MWA data I: Foregrounds and preliminary upper limits
Sukhdeep Singh Gill, Somnath Bharadwaj, Khandakar Md Asif Elahi, Shiv K. Sethi, Akash Kumar Patwa
https://arxiv.org/abs/2507.04964

The EoR 21-cm Bispectrum at $z=8.2$ from MWA data I: Foregrounds and preliminary upper limits
We attempt to measure the $z = 8.2$ Epoch of Reionization (EoR) 21-cm bispectrum (BS) using Murchison Widefield Array (MWA) $154.2~\mathrm{MHz}$ data. We find that $B(k_{1\perp}, k_{2\perp}, k_{3\perp}, k_{1\parallel}, k_{2\parallel})$ the 3D cylindrical BS exhibits a foreground wedge, similar to $P(k_{1\perp},k_{1\parallel})$ the 21-cm cylindrical power spectrum. However, the BS foreground wedge, which depends on $(k_{1\perp},k_{1\parallel})$, $(k_{2\perp},k_{2\parallel})$ and $(k_{3\perp},k_{…

PRISM: Pointcloud Reintegrated Inference via Segmentation and Cross-attention for Manipulation
Daqi Huang, Zhehao Cai, Yuzhi Hao, Zechen Li, Chee-Meng Chew
https://arxiv.org/abs/2507.04633

PRISM: Pointcloud Reintegrated Inference via Segmentation and Cross-attention for Manipulation
Robust imitation learning for robot manipulation requires comprehensive 3D perception, yet many existing methods struggle in cluttered environments. Fixed camera view approaches are vulnerable to perspective changes, and 3D point cloud techniques often limit themselves to keyframes predictions, reducing their efficacy in dynamic, contact-intensive tasks. To address these challenges, we propose PRISM, designed as an end-to-end framework that directly learns from raw point cloud observations and …

Great new :qgis: initiative by @… and @…:
Make #QGIS an open platform for building geospatial

QGIS 3D for Open Source Digital Twins | Lutra Consulting
Join our crowdfunding campaign to enhance QGIS 3D tools for open-source digital twins, bringing improved performance, features, and community-driven innovation.

SVD: Spatial Video Dataset
M. H. Izadimehr, Milad Ghanbari, Guodong Chen, Wei Zhou, Xiaoshuai Hao, Mallesham Dasari, Christian Timmerer, Hadi Amirpour
https://arxiv.org/abs/2506.06037

SVD: Spatial Video Dataset
Stereoscopic video has long been the subject of research due to its capacity to deliver immersive three-dimensional content across a wide range of applications, from virtual and augmented reality to advanced human-computer interaction. The dual-view format inherently provides binocular disparity cues that enhance depth perception and realism, making it indispensable for fields such as telepresence, 3D mapping, and robotic vision. Until recently, however, end-to-end pipelines for capturing, enco…

One Video to Steal Them All: 3D-Printing IP Theft through Optical Side-Channels
Twisha Chattopadhyay, Fabricio Ceschin, Marco E. Garza, Dymytriy Zyunkin, Animesh Chhotaray, Aaron P. Stebner, Saman Zonouz, Raheem Beyah
https://arxiv.org/abs/2506.21897

One Video to Steal Them All: 3D-Printing IP Theft through Optical Side-Channels
The 3D printing industry is rapidly growing and increasingly adopted across various sectors including manufacturing, healthcare, and defense. However, the operational setup often involves hazardous environments, necessitating remote monitoring through cameras and other sensors, which opens the door to cyber-based attacks. In this paper, we show that an adversary with access to video recordings of the 3D printing process can reverse engineer the underlying 3D print instructions. Our model tracks…

Global strong solution of the 3D compressible liquid crystal flows with density-dependent viscosity and large velocity
Jiaxu Li, Yu Mei, Rong Zhang
https://arxiv.org/abs/2507.04760

Global strong solution of the 3D compressible liquid crystal flows with density-dependent viscosity and large velocity
This paper concerns the Cauchy problem of three-dimensional compressible liquid crystal flows with density-dependent viscosity. When the viscosity coefficients $μ_1(ρ),μ_2(ρ)$ are power functions of the density with the power larger than $1$, it is proved that the system exists a unique global strong solution as long as the initial density is sufficiently large and $L^3$-norm of the derivative of the initial director is sufficiently small. This is the first result concerning the global stro…

A3FR: Agile 3D Gaussian Splatting with Incremental Gaze Tracked Foveated Rendering in Virtual Reality
Shuo Xin, Haiyu Wang, Sai Qian Zhang
https://arxiv.org/abs/2507.04147

A3FR: Agile 3D Gaussian Splatting with Incremental Gaze Tracked Foveated Rendering in Virtual Reality
Virtual reality (VR) significantly transforms immersive digital interfaces, greatly enhancing education, professional practices, and entertainment by increasing user engagement and opening up new possibilities in various industries. Among its numerous applications, image rendering is crucial. Nevertheless, rendering methodologies like 3D Gaussian Splatting impose high computational demands, driven predominantly by user expectations for superior visual quality. This results in notable processing…

DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling
Hangyu Ji
https://arxiv.org/abs/2506.05297 https://

DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling
Accurate 3D medical image segmentation demands architectures capable of reconciling global context modeling with spatial topology preservation. While State Space Models (SSMs) like Mamba show potential for sequence modeling, existing medical SSMs suffer from encoder-decoder incompatibility: the encoder's 1D sequence flattening compromises spatial structures, while conventional decoders fail to leverage Mamba's state propagation. We present DM-SegNet, a Dual-Mamba architecture integrating direct…

Conversational Interfaces for Parametric Conceptual Architectural Design: Integrating Mixed Reality with LLM-driven Interaction
Ruochen Ji, Lyu Tiangang
https://arxiv.org/abs/2506.06066

Conversational Interfaces for Parametric Conceptual Architectural Design: Integrating Mixed Reality with LLM-driven Interaction
Mixed reality (MR) environments offer embodied spatial interaction, providing intuitive 3D manipulation capabilities that enhance the conceptual design process. Parametric modeling, a powerful and advanced architectural design method, enables the generation of complex, optimized geometries. However, its integration into MR environments remains limited due to precision constraints and unsuitable input modalities. Existing MR tools prioritize spatial interaction but lack the control and expressiv…

Circular Holographic MIMO Beamforming for Integrated Data and Energy Multicast Systems
Qingxiao Huang, Yizhe Zhao, Jie Hu, Kun Yang, Yuguang Fang
https://arxiv.org/abs/2507.05057 …

Circular Holographic MIMO Beamforming for Integrated Data and Energy Multicast Systems
Thanks to the application of metamaterials, holographic multiple-input multiple-output (H-MIMO) is expected to achieve a higher spatial diversity gain with lower hardware complexity. With the aid of a circular antenna arrangement of H-MIMO, integrated data and energy multicast (IDEM) can fully exploit the near-field channel to realize wider range of energy focusing and higher achievable rate. In this paper, we derive the closed-form near-field resolution function in 3D space and show the asympt…

Speculative Evolution Through 3D Cellular Automata
Amir Hossein Khazaei
https://arxiv.org/abs/2505.01692 https://arxiv.org/pdf/2505.0…

Speculative Evolution Through 3D Cellular Automata
This project explores speculative evolution through a 3D implementation of Conway's Game of Life, using procedural simulation to generate unfamiliar extraterrestrial organic forms. By applying a volumetric optimized workflow, the raw cellular structures are smoothed into unified, bone-like geometries that resemble hypothetical non-terrestrial morphologies. The resulting forms, strange yet organic, are 3D printed as fossil-like artifacts, presenting a tangible representation of generative struct…

Spontaneous stochasticity in the fluctuating Navier-Stokes equations on a logarithmic lattice
Erika Ortiz, Ciro S. Campolina, Alexei A. Mailybaev
https://arxiv.org/abs/2507.03196 …

Spontaneous stochasticity in the fluctuating Navier-Stokes equations on a logarithmic lattice
The predictability of turbulent flows remains a challenging problem for mathematicians, physicists, and meteorologists. In this context, we consider the 3D incompressible Navier-Stokes equations with small-scale random forcing on logarithmic lattices in Fourier space. Our goal is to probe the phenomenon of spontaneous stochasticity in this system, which means that its solutions remain stochastic in the limit of vanishing viscosity and noise. For this, we consider numerical simulations with incr…

This https://arxiv.org/abs/2505.24305 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
Recent advancements in 3D robotic manipulation have improved grasping of everyday objects, but transparent and specular materials remain challenging due to depth sensing limitations. While several 3D reconstruction and depth completion approaches address these challenges, they suffer from setup complexity or limited observation information utilization. To address this, leveraging the power of single view 3D object reconstruction approaches, we propose a training free framework SR3D that enables…

Physics-informed neural networks and neural operators for a study of EUV electromagnetic wave diffraction from a lithography mask
Vasiliy A. Es'kin, Egor V. Ivanov
https://arxiv.org/abs/2507.04153

Physics-informed neural networks and neural operators for a study of EUV electromagnetic wave diffraction from a lithography mask
Physics-informed neural networks (PINNs) and neural operators (NOs) for solving the problem of diffraction of Extreme Ultraviolet (EUV) electromagnetic waves from a mask are presented. A novel hybrid Waveguide Neural Operator (WGNO) is introduced, which is based on a waveguide method with its most computationally expensive part replaced by a neural network. Numerical experiments on realistic 2D and 3D masks show that the WGNO achieves state-of-the-art accuracy and inference time, providing a hi…

Resurgence of CO in a warm bubble around accreting protoplanets and its observability
O. Chrenko, S. Casassus, R. O. Chametla
https://arxiv.org/abs/2507.03370

Resurgence of CO in a warm bubble around accreting protoplanets and its observability
The cold outer regions of protoplanetary disks are expected to contain a midplane-centered layer in which gas-phase CO molecules freeze-out and their overall abundance is low. The layer then manifests itself as a void in the channel maps of CO rotational emission lines. We explore whether the frozen-out layer can expose the circumplanetary environment of embedded accreting protoplanets to observations. To this end, we performed 3D radiative gas-dust hydrodynamic simulations, directly linking op…

Bayesian network 3D event reconstruction in the Cygno optical TPC for dark matter direct detection
Fernando Domingues Amaro, Rita Antonietti, Elisabetta Baracchini, Luigi Benussi, Stefano Bianco, Francesco Borra, Cesidio Capoccia, Michele Caponero, Gianluca Cavoto, Igor Abritta Costa, Antonio Croce, Emiliano Dan\'e, Melba D'Astolfo, Giorgio Dho, Flaminia Di Giambattista, Emanuele Di Marco, Giulia D'Imperio, Matteo Folcarelli, Joaquim Marques Ferreira dos Santos, Davide Fior…

Bayesian network 3D event reconstruction in the Cygno optical TPC for dark matter direct detection
The CYGNO experiment is developing a high-resolution gaseous Time Projection Chamber with optical readout for directional dark matter searches. The detector uses a helium-tetrafluoromethane (He:CF$_4$ 60:40) gas mixture at atmospheric pressure and a triple Gas Electron Multiplier amplification stage, coupled with a scientific camera for high-resolution 2D imaging and fast photomultipliers for time-resolved scintillation light detection. This setup enables 3D event reconstruction: photomultiplie…

All in One: Visual-Description-Guided Unified Point Cloud Segmentation
Zongyan Han, Mohamed El Amine Boudjoghra, Jiahua Dong, Jinhong Wang, Rao Muhammad Anwer
https://arxiv.org/abs/2507.05211

All in One: Visual-Description-Guided Unified Point Cloud Segmentation
Unified segmentation of 3D point clouds is crucial for scene understanding, but is hindered by its sparse structure, limited annotations, and the challenge of distinguishing fine-grained object classes in complex environments. Existing methods often struggle to capture rich semantic and contextual information due to limited supervision and a lack of diverse multimodal cues, leading to suboptimal differentiation of classes and instances. To address these challenges, we propose VDG-Uni3DSeg, a no…

This https://arxiv.org/abs/2505.09708 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

The uncertainty of magnetic fields in 3D non-local thermodynamic equilibrium inversions
We describe our approach to solve the problem of ensuring the solenoidality of the magnetic field vector in three-dimensional (3D) inversions, as well as the estimation of the uncertainty in the inferred magnetic field. The solenoidality of the magnetic field vector is often disregarded in the inversion of spectropolarimetric data due to limitations in the traditional one-dimensional inversion techniques. We propose a method to ensure the solenoidal condition in 3D inversions based on our meshf…

LATENTRED main board layout progress: got most of the GTYs and FPGA-MCU paths done, as well as the RGMII PHY.
Still lots more to do but I'm liking the floorplan, at least the parts that I've done.
I'm debating moving the RGMII PHY to the west a bit and adding a fan cutout directly behind the FPGA so that I can have it suck exhaust air right past the FPGA (possibly with a 3d printed air dam or something in the future). Will need to spend some time thinking about therma…

PLUS: Plug-and-Play Enhanced Liver Lesion Diagnosis Model on Non-Contrast CT Scans
Jiacheng Hao, Xiaoming Zhang, Wei Liu, Xiaoli Yin, Yuan Gao, Chunli Li, Ling Zhang, Le Lu, Yu Shi, Xu Han, Ke Yan
https://arxiv.org/abs/2507.03872

PLUS: Plug-and-Play Enhanced Liver Lesion Diagnosis Model on Non-Contrast CT Scans
Focal liver lesions (FLL) are common clinical findings during physical examination. Early diagnosis and intervention of liver malignancies are crucial to improving patient survival. Although the current 3D segmentation paradigm can accurately detect lesions, it faces limitations in distinguishing between malignant and benign liver lesions, primarily due to its inability to differentiate subtle variations between different lesions. Furthermore, existing methods predominantly rely on specialized …

Astronomy as a strategic driver for sustainable development: #Astronomy for Development is to direct astronomy towards addressing urgent societal needs.

SurGSplat: Progressive Geometry-Constrained Gaussian Splatting for Surgical Scene Reconstruction
Yuchao Zheng, Jianing Zhang, Guochen Ning, Hongen Liao
https://arxiv.org/abs/2506.05935

SurGSplat: Progressive Geometry-Constrained Gaussian Splatting for Surgical Scene Reconstruction
Intraoperative navigation relies heavily on precise 3D reconstruction to ensure accuracy and safety during surgical procedures. However, endoscopic scenarios present unique challenges, including sparse features and inconsistent lighting, which render many existing Structure-from-Motion (SfM)-based methods inadequate and prone to reconstruction failure. To mitigate these constraints, we propose SurGSplat, a novel paradigm designed to progressively refine 3D Gaussian Splatting (3DGS) through the …

A framework for 3D interaction techniques
Pablo Figueroa, Mark Green, Benjamin Watson
https://arxiv.org/abs/2507.02254 https://arxiv.…

A framework for 3D interaction techniques
This paper presents a software architecture for 3D interaction techniques (ITs) and an object oriented, toolkit-independent framework that implements such architecture. ITs are composed of basic filters connected in a dataflow, where virtual input devices and objects in the scene are sources of information. An execution model defines the general flow of information between filters. This framework has been designed to be extensible: new information types, new input devices, new execution models,…

Hybrid Ensemble of Segmentation-Assisted Classification and GBDT for Skin Cancer Detection with Engineered Metadata and Synthetic Lesions from ISIC 2024 Non-Dermoscopic 3D-TBP Images
Muhammad Zubair Hasan, Fahmida Yasmin Rifat
https://arxiv.org/abs/2506.03420

Hybrid Ensemble of Segmentation-Assisted Classification and GBDT for Skin Cancer Detection with Engineered Metadata and Synthetic Lesions from ISIC 2024 Non-Dermoscopic 3D-TBP Images
Skin cancer is among the most prevalent and life-threatening diseases worldwide, with early detection being critical to patient outcomes. This work presents a hybrid machine and deep learning-based approach for classifying malignant and benign skin lesions using the SLICE-3D dataset from ISIC 2024, which comprises 401,059 cropped lesion images extracted from 3D Total Body Photography (TBP), emulating non-dermoscopic, smartphone-like conditions. Our method combines vision transformers (EVA02) an…

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
Yuqi Wu, Wenzhao Zheng, Jie Zhou, Jiwen Lu
https://arxiv.org/abs/2507.02863 https…

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
Dense 3D scene reconstruction from an ordered sequence or unordered image collections is a critical step when bringing research in computer vision into practical scenarios. Following the paradigm introduced by DUSt3R, which unifies an image pair densely into a shared coordinate system, subsequent methods maintain an implicit memory to achieve dense 3D reconstruction from more images. However, such implicit memory is limited in capacity and may suffer from information loss of earlier frames. We …

Bastelprojekt: 3D-gedruckte VTOL-Drohne fliegt knapp 210 km mit einer Ladung
Ohne große Kenntnisse über Aerodynamik und CAD entwickelte ein Bastler eine VTOL-Drohne mit hoher Reichweite. Die meisten Bauteile stammen aus dem 3D-Drucker.

Finished laying out the northwest corner. I think this is pretty final in that area, but I'm going to move the fan connectors and actually put one of the fans where they are.

My partner asked for a last minute sign today. 3D printing to the rescue!
Made a sign for today… 3D printed letters, foam core, spray paint… then added a 3D printed handle.
#noKings #resist #resistFascism

SPIDER: Structure-Preferential Implicit Deep Network for Biplanar X-ray Reconstruction
Tianqi Yu, Xuanyu Tian, Jiawen Yang, Dongming He, Jingyi Yu, Xudong Wang, Yuyao Zhang
https://arxiv.org/abs/2507.04684

SPIDER: Structure-Preferential Implicit Deep Network for Biplanar X-ray Reconstruction
Biplanar X-ray imaging is widely used in health screening, postoperative rehabilitation evaluation of orthopedic diseases, and injury surgery due to its rapid acquisition, low radiation dose, and straightforward setup. However, 3D volume reconstruction from only two orthogonal projections represents a profoundly ill-posed inverse problem, owing to the intrinsic lack of depth information and irreducible ambiguities in soft-tissue visualization. Some existing methods can reconstruct skeletal stru…

Object-centric 3D Motion Field for Robot Learning from Human Videos
Zhao-Heng Yin, Sherry Yang, Pieter Abbeel
https://arxiv.org/abs/2506.04227 https://

Object-centric 3D Motion Field for Robot Learning from Human Videos
Learning robot control policies from human videos is a promising direction for scaling up robot learning. However, how to extract action knowledge (or action representations) from videos for policy learning remains a key challenge. Existing action representations such as video frames, pixelflow, and pointcloud flow have inherent limitations such as modeling complexity or loss of information. In this paper, we propose to use object-centric 3D motion field to represent actions for robot learning …

This https://arxiv.org/abs/2506.00512 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csGR_…

Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing
Text-guided 3D editing aims to precisely edit semantically relevant local 3D regions, which has significant potential for various practical applications ranging from 3D games to film production. Existing methods typically follow a view-indiscriminate paradigm: editing 2D views indiscriminately and projecting them back into 3D space. However, they overlook the different cross-view interdependencies, resulting in inconsistent multi-view editing. In this study, we argue that ideal consistent 3D ed…

Retro-Emulator "3dSen VR“ macht 2D-Klassiker in 3D und Virtual Reality spielbar
Mit dem Emulator "3dSen VR" können Retro-Fans geliebte 2D-NES-Klassiker erstmals in vollständigen 3D-Dioramen erleben – auch in Virtual Reality.

Hybrid-View Attention for csPCa Classification in TRUS
Zetian Feng, Juan Fu, Xuebin Zou, Hongsheng Ye, Hong Wu, Jianhua Zhou, Yi Wang
https://arxiv.org/abs/2507.03421

Hybrid-View Attention for csPCa Classification in TRUS
Prostate cancer (PCa) is a leading cause of cancer-related mortality in men, and accurate identification of clinically significant PCa (csPCa) is critical for timely intervention. Transrectal ultrasound (TRUS) is widely used for prostate biopsy; however, its low contrast and anisotropic spatial resolution pose diagnostic challenges. To address these limitations, we propose a novel hybrid-view attention (HVA) network for csPCa classification in 3D TRUS that leverages complementary information fr…

VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection
Wuyang Li, Zhu Yu, Alexandre Alahi
https://arxiv.org/abs/2506.04623 https://

VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection
3D semantic occupancy prediction aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate it as a dense segmentation task, independently classifying each voxel. However, this paradigm neglects critical instance-centric discriminability, leading to instance-level incompleteness and adjacent ambiguities. To address this, we highlight a free lunch of occupancy labels: the voxel-level class label implicitly provides i…

LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
Fangfu Liu, Hao Li, Jiawei Chi, Hanyang Wang, Minghui Yang, Fudong Wang, Yueqi Duan
https://arxiv.org/abs/2507.02813

LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
Recovering 3D structures with open-vocabulary scene understanding from 2D images is a fundamental but daunting task. Recent developments have achieved this by performing per-scene optimization with embedded language information. However, they heavily rely on the calibrated dense-view reconstruction paradigm, thereby suffering from severe rendering artifacts and implausible semantic synthesis when limited views are available. In this paper, we introduce a novel generative framework, coined LangS…

Dreidimensionale Karten der Atmosphäre: Europäischer Wettersatellit soll starten
In der Nacht soll Europas erster Erdbeobachtungssatellit starten, der nicht nur auf die Atmosphäre gucken soll. Liefern soll die 3D-Sicht ein Infrarotsensor.

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
Ishika Singh, Ankit Goyal, Stan Birchfield, Dieter Fox, Animesh Garg, Valts Blukis
https://arxiv.org/abs/2506.01196

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies. We address the challenge of mapping natural language instructions and multi-view RGBD observations to quasi-static robot actions. 3D-aware robot policies achieve state-of-the-art performance on precise robot manipulation tasks, but struggle with generalization to unseen instructions, scenes, and objects. On …

LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans
Zhening Huang, Xiaoyang Wu, Fangcheng Zhong, Hengshuang Zhao, Matthias Nie{\ss}ner, Joan Lasenby
https://arxiv.org/abs/2507.02861

LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans
We propose LiteReality, a novel pipeline that converts RGB-D scans of indoor environments into compact, realistic, and interactive 3D virtual replicas. LiteReality not only reconstructs scenes that visually resemble reality but also supports key features essential for graphics pipelines -- such as object individuality, articulation, high-quality physically based rendering materials, and physically based interaction. At its core, LiteReality first performs scene understanding and parses the resu…

3D Heart Reconstruction from Sparse Pose-agnostic 2D Echocardiographic Slices
Zhurong Chen, Jinhua Chen, Wei Zhuo, Wufeng Xue, Dong Ni
https://arxiv.org/abs/2507.02411

3D Heart Reconstruction from Sparse Pose-agnostic 2D Echocardiographic Slices
Echocardiography (echo) plays an indispensable role in the clinical practice of heart diseases. However, ultrasound imaging typically provides only two-dimensional (2D) cross-sectional images from a few specific views, making it challenging to interpret and inaccurate for estimation of clinical parameters like the volume of left ventricle (LV). 3D ultrasound imaging provides an alternative for 3D quantification, but is still limited by the low spatial and temporal resolution and the highly dema…

ArtGS:3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects
Qiaojun Yu, Xibin Yuan, Yu jiang, Junting Chen, Dongzhe Zheng, Ce Hao, Yang You, Yixing Chen, Yao Mu, Liu Liu, Cewu Lu
https://arxiv.org/abs/2507.02600

ArtGS:3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects
Articulated object manipulation remains a critical challenge in robotics due to the complex kinematic constraints and the limited physical reasoning of existing methods. In this work, we introduce ArtGS, a novel framework that extends 3D Gaussian Splatting (3DGS) by integrating visual-physical modeling for articulated object understanding and interaction. ArtGS begins with multi-view RGB-D reconstruction, followed by reasoning with a vision-language model (VLM) to extract semantic and structura…

HP Dimension: Googles 3D-Videokonferenzlösung Beam hat einen hohen Preis
HP hat mit dem Dimension ein erstes marktreifes 3D-Videokonferenzsystem angekündigt, das auf Google Beam, auch bekannt als Project Starlink, setzt.  

Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing
Yang Zheng, Mengqi Huang, Nan Chen, Zhendong Mao
https://arxiv.org/abs/2506.00512

Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing
Text-guided 3D editing aims to precisely edit semantically relevant local 3D regions, which has significant potential for various practical applications ranging from 3D games to film production. Existing methods typically follow a view-indiscriminate paradigm: editing 2D views indiscriminately and projecting them back into 3D space. However, they overlook the different cross-view interdependencies, resulting in inconsistent multi-view editing. In this study, we argue that ideal consistent 3D ed…

HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars
Gent Serifi, Marcel C. B\"uhler
https://arxiv.org/abs/2507.02803

HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars
We introduce HyperGaussians, a novel extension of 3D Gaussian Splatting for high-quality animatable face avatars. Creating such detailed face avatars from videos is a challenging problem and has numerous applications in augmented and virtual reality. While tremendous successes have been achieved for static faces, animatable avatars from monocular videos still fall in the uncanny valley. The de facto standard, 3D Gaussian Splatting (3DGS), represents a face through a collection of 3D Gaussian pr…

Rethink 3D Object Detection from Physical World
Satoshi Tanaka, Koji Minoda, Fumiya Watanabe, Takamasa Horibe
https://arxiv.org/abs/2507.00190 https://

Rethink 3D Object Detection from Physical World
High-accuracy and low-latency 3D object detection is essential for autonomous driving systems. While previous studies on 3D object detection often evaluate performance based on mean average precision (mAP) and latency, they typically fail to address the trade-off between speed and accuracy, such as 60.0 mAP at 100 ms vs 61.0 mAP at 500 ms. A quantitative assessment of the trade-offs between different hardware devices and accelerators remains unexplored, despite being critical for real-time appl…

AMD gibt proprietäre 3D-Grafiktreiber für Linux auf
Auch im professionellen Umfeld setzt AMD zur 3D- und Video-Beschleunigung auf quelloffene Treiber, die Linux-Distributionen seit langem standardmäßig nutzen.

Towards the target and not beyond: 2d vs 3d visual aids in mr-based neurosurgical simulation
Pasquale Cascarano, Andrea Loretti, Matteo Martinoni, Luca Zanuttini, Alessio Di Pasquale, Gustavo Marfia
https://arxiv.org/abs/2506.05164

Towards the target and not beyond: 2d vs 3d visual aids in mr-based neurosurgical simulation
Neurosurgery increasingly uses Mixed Reality (MR) technologies for intraoperative assistance. The greatest challenge in this area is mentally reconstructing complex 3D anatomical structures from 2D slices with millimetric precision, which is required in procedures like External Ventricular Drain (EVD) placement. MR technologies have shown great potential in improving surgical performance, however, their limited availability in clinical settings underscores the need for training systems that fos…

SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting
Yiming Huang, Long Bai, Beilei Cui, Kun Yuan, Guankun Wang, Mobarakol Islam, Nicolas Padoy, Nassir Navab, Hongliang Ren
https://arxiv.org/abs/2506.23309

SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting
In contemporary surgical research and practice, accurately comprehending 3D surgical scenes with text-promptable capabilities is particularly crucial for surgical planning and real-time intra-operative guidance, where precisely identifying and interacting with surgical tools and anatomical structures is paramount. However, existing works focus on surgical vision-language model (VLM), 3D reconstruction, and segmentation separately, lacking support for real-time text-promptable 3D queries. In thi…

Novel Design of 3D Printed Tumbling Microrobots for in vivo Targeted Drug Delivery
Aaron C. Davis, Siting Zhang, Adalyn Meeks, Diya Sakhrani, Luis Carlos Sanjuan Acosta, D. Ethan Kelley, Emma Caldwell, Luis Solorio, Craig J. Goergen, David J. Cappelleri
https://arxiv.org/abs/2507.00166

Novel Design of 3D Printed Tumbling Microrobots for in vivo Targeted Drug Delivery
This paper presents innovative designs for 3D-printed tumbling microrobots, specifically engineered for targeted in vivo drug delivery applications. The microrobot designs, created using stereolithography 3D printing technologies, incorporate permanent micro-magnets to enable actuation via a rotating magnetic field actuator system. The experimental framework encompasses a series of locomotion characterization tests to evaluate microrobot performance under various conditions. Testing variables i…

This https://arxiv.org/abs/2505.18924 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point CLoud Active Learning
We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical label structures and guide uncertainty-based sample selection. Unlike prior methods that treat labels as flat and independent, our approach leverages LLM prompting to automatically generate multi-level semantic taxonomies and introduces a recursive uncertainty projection mechanism that propagates uncertainty across hier…

Gbake: Baking 3D Gaussian Splats into Reflection Probes
Stephen Pasch, Joel K. Salzman, Changxi Zheng
https://arxiv.org/abs/2507.02257 https://

Gbake: Baking 3D Gaussian Splats into Reflection Probes
The growing popularity of 3D Gaussian Splatting has created the need to integrate traditional computer graphics techniques and assets in splatted environments. Since 3D Gaussian primitives encode lighting and geometry jointly as appearance, meshes are relit improperly when inserted directly in a mixture of 3D Gaussians and thus appear noticeably out of place. We introduce GBake, a specialized tool for baking reflection probes from Gaussian-splatted scenes that enables realistic reflection mappi…

Real-Time 3D Guidewire Reconstruction from Intraoperative DSA Images for Robot-Assisted Endovascular Interventions
Tianliang Yao, Bingrui Li, Bo Lu, Zhiqiang Pei, Yixuan Yuan, Peng Qi
https://arxiv.org/abs/2506.21631

Real-Time 3D Guidewire Reconstruction from Intraoperative DSA Images for Robot-Assisted Endovascular Interventions
Accurate three-dimensional (3D) reconstruction of guidewire shapes is crucial for precise navigation in robot-assisted endovascular interventions. Conventional 2D Digital Subtraction Angiography (DSA) is limited by the absence of depth information, leading to spatial ambiguities that hinder reliable guidewire shape sensing. This paper introduces a novel multimodal framework for real-time 3D guidewire reconstruction, combining preoperative 3D Computed Tomography Angiography (CTA) with intraopera…

SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting
Shengjie Lin, Jiading Fang, Muhammad Zubair Irshad, Vitor Campagnolo Guizilini, Rares Andrei Ambrus, Greg Shakhnarovich, Matthew R. Walter
https://arxiv.org/abs/2506.03594

SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting
Reconstructing articulated objects prevalent in daily environments is crucial for applications in augmented/virtual reality and robotics. However, existing methods face scalability limitations (requiring 3D supervision or costly annotations), robustness issues (being susceptible to local optima), and rendering shortcomings (lacking speed or photorealism). We introduce SplArt, a self-supervised, category-agnostic framework that leverages 3D Gaussian Splatting (3DGS) to reconstruct articulated ob…

PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation
Mert Kiray, Paul Uhlenbruck, Nassir Navab, Benjamin Busam
https://arxiv.org/abs/2506.01091

PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation
Visual effects (VFX) are key to immersion in modern films, games, and AR/VR. Creating 3D effects requires specialized expertise and training in 3D animation software and can be time consuming. Generative solutions typically rely on computationally intense methods such as diffusion models which can be slow at 4D inference. We reformulate 3D animation as a field prediction task and introduce a text-driven framework that infers a time-varying 4D flow field acting on 3D Gaussians. By leveraging lar…

Neural Visibility Cache for Real-Time Light Sampling
Jakub Bok\v{s}ansk\'y, Daniel Meister
https://arxiv.org/abs/2506.05930 https://

Neural Visibility Cache for Real-Time Light Sampling
Direct illumination with many lights is an inherent component of physically-based rendering, remaining challenging, especially in real-time scenarios. We propose an online-trained neural cache that stores visibility between lights and 3D positions. We feed light visibility to weighted reservoir sampling (WRS) to sample a light source. The cache is implemented as a fully-fused multilayer perceptron (MLP) with multi-resolution hash-grid encoding, enabling online training and efficient inference o…

Replaced article(s) found for cs.GR. https://arxiv.org/list/cs.GR/new
[1/1]:
- Anymate: A Dataset and Baselines for Learning 3D Object Rigging
Yufan Deng, Yuhao Zhang, Chen Geng, Shangzhe Wu, Jiajun Wu