Tootfinder

Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions
AmirHossein Naghi Razlighi, Elaheh Badali Golezani, Shohreh Kasaei
https://arxiv.org/abs/2506.22973

Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions
3D Gaussian Splatting enables high-quality real-time rendering but often produces millions of splats, resulting in excessive storage and computational overhead. We propose a novel lossy compression method based on learnable confidence scores modeled as Beta distributions. Each splat's confidence is optimized through reconstruction-aware losses, enabling pruning of low-confidence splats while preserving visual fidelity. The proposed approach is architecture-agnostic and can be applied to any Gau…

DIGS: Dynamic CBCT Reconstruction using Deformation-Informed 4D Gaussian Splatting and a Low-Rank Free-Form Deformation Model
Yuliang Huang, Imraj Singh, Thomas Joyce, Kris Thielemans, Jamie R. McClelland
https://arxiv.org/abs/2506.22280

DIGS: Dynamic CBCT Reconstruction using Deformation-Informed 4D Gaussian Splatting and a Low-Rank Free-Form Deformation Model
3D Cone-Beam CT (CBCT) is widely used in radiotherapy but suffers from motion artifacts due to breathing. A common clinical approach mitigates this by sorting projections into respiratory phases and reconstructing images per phase, but this does not account for breathing variability. Dynamic CBCT instead reconstructs images at each projection, capturing continuous motion without phase sorting. Recent advancements in 4D Gaussian Splatting (4DGS) offer powerful tools for modeling dynamic scenes, …

Exciting new ground in Centrist science being broken in the Irish Times this morning.
Splitting the very atom of meaning to reveal this previously only-theorised new Centrist element fused within:

The Python-based data-exfiltration utility used by the Cl0p ransomware group (commonly distributed as part of the toolset during the 2023 – 2024 MoveIt campaigns) constructs operating-system commands by directly concatenating attacker-supplied strings without input sanitization. An authenticated endpoint on the Cl0p operators’ staging/collection host passes file-or directory-names received from compromised machines straight into a shell-escape sequence. No official patch or cooperation from …

Bilan de "poc-sveltekit-custom-server" pour exécuter des tâches "cron" dans un projet Monolith en SvelteKit :
#Sveltekit

Uteserveringarna är fulla av folk sedan flera timmar. Volymen höjs steg för steg på storbildsskärmarna.
Småpojkar spelade fotboll i gränderna i eftermiddags.
Men nu är det snart match.
#ChampionsLeague-feber. #Paris

SAR-GS: 3D Gaussian Splatting for Synthetic Aperture Radar Target Reconstruction
Aobo Li, Zhengxin Lei, Jiangtao Wei, Feng Xu
https://arxiv.org/abs/2506.21633

SAR-GS: 3D Gaussian Splatting for Synthetic Aperture Radar Target Reconstruction
Three-dimensional target reconstruction from synthetic aperture radar (SAR) imagery is crucial for interpreting complex scattering information in SAR data. However, the intricate electromagnetic scattering mechanisms inherent to SAR imaging pose significant reconstruction challenges. Inspired by the remarkable success of 3D Gaussian Splatting (3D-GS) in optical domain reconstruction, this paper presents a novel SAR Differentiable Gaussian Splatting Rasterizer (SDGR) specifically designed for SA…

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…

VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding
Minchao Jiang, Shunyu Jia, Jiaming Gu, Xiaoyuan Lu, Guangming Zhu, Anqi Dong, Liang Zhang
https://arxiv.org/abs/2506.22799

VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding
3D Gaussian Splatting (3DGS) has become horsepower in high-quality, real-time rendering for novel view synthesis of 3D scenes. However, existing methods focus primarily on geometric and appearance modeling, lacking deeper scene understanding while also incurring high training costs that complicate the originally streamlined differentiable rendering pipeline. To this end, we propose VoteSplat, a novel 3D scene understanding framework that integrates Hough voting with 3DGS. Specifically, Segment …

ICP-3DGS: SfM-free 3D Gaussian Splatting for Large-scale Unbounded Scenes
Chenhao Zhang, Yezhi Shen, Fengqing Zhu
https://arxiv.org/abs/2506.21629 https://…

ICP-3DGS: SfM-free 3D Gaussian Splatting for Large-scale Unbounded Scenes
In recent years, neural rendering methods such as NeRFs and 3D Gaussian Splatting (3DGS) have made significant progress in scene reconstruction and novel view synthesis. However, they heavily rely on preprocessed camera poses and 3D structural priors from structure-from-motion (SfM), which are challenging to obtain in outdoor scenarios. To address this challenge, we propose to incorporate Iterative Closest Point (ICP) with optimization-based refinement to achieve accurate camera pose estimation…