Tootfinder

SAM4D: Segment Anything in Camera and LiDAR Streams
Jianyun Xu, Song Wang, Ziqian Ni, Chunyong Hu, Sheng Yang, Jianke Zhu, Qiang Li
https://arxiv.org/abs/2506.21547

SAM4D: Segment Anything in Camera and LiDAR Streams
We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) is introduced to align camera and LiDAR features in a shared 3D space, enabling seamless cross-modal prompting and interaction. Additionally, we propose Motion-aware Cross-modal Memory Attention (MCMA), which leverages ego-motion compensation to enhance temporal consistency and long-horizon feature retrieval, ensuring …

Meta verarbeitet jetzt eure Fotos. Ob da wohl Palantir mit gefüttert wird. Das hätte dann zur Folge, dass einige deutsche Polizeien und natürlich das gesamte amerikanische Law Enforcement automatisiert mit euren Fotos fahnden kann.
Big Brother auf Steroiden.
#Überwachung #meta

Ring rolls out Video Descriptions, an AI-powered beta feature that generates text summaries of motion activity from its doorbells and cameras (Jennifer Pattison Tuohy/The Verge)
https://www.theverge.com/news/692523/ring-ai-powe…

Ring camera alerts are about to get a lot smarter
Ring’s new Video Descriptions feature will tell you what your video doorbell or security camera sees, so you don’t have to watch the video.

A Computationally Aware Multi Objective Framework for Camera LiDAR Calibration
Venkat Karramreddy, Rangarajan Ramanujam
https://arxiv.org/abs/2506.20636 ht…

A Computationally Aware Multi Objective Framework for Camera LiDAR Calibration
Accurate extrinsic calibration between LiDAR and camera sensors is important for reliable perception in autonomous systems. In this paper, we present a novel multi-objective optimization framework that jointly minimizes the geometric alignment error and computational cost associated with camera-LiDAR calibration. We optimize two objectives: (1) error between projected LiDAR points and ground-truth image edges, and (2) a composite metric for computational cost reflecting runtime and resource usa…

https://www.theregister.com/2025/06/24/vera_galaxy_camera

"Sie empfinden jeden Angriff auf irgendeinen Aspekt des räuberischen Kapitalismus als Angriff auf sich selbst" - dieser Satz beschreibt ziemlich gut das Selbstverständnis der dominierenden deutschen Politikjournalisten.
@… im @…

I have a little audio challenge for y'all, as I do not believe what needs to happen can currently be done:
I was doing an interview recently and the camera folx messed up and now the only audio has some song playing almost louder than my voice in the background!
Problem was that that song almost only had loud vocals. Any AI filter I'd find online to filter out background noise or sounds would still only extract both my voice and the song's vocals.
Luckily…

Erik-Uden-Audio-Challenge
Linksjugend ['solid] Cloud

Found the specs sheet.
The front camera and ultrawide camera seem to be considerably worse.
The normal wide camera seems to be better, except it lost the electronic stabilisation (not sure how important that is tbh).
The battery is better, but it needs a screwdriver to be changed so no more switch during the day if you don’t have a screwdriver always on you. This comes with no added water resistance, which makes me wonder why they did this.
The display seems to be worse? The resolution is smaller which makes sense since the size is smaller, but also it seems to have less PPI than the Fairphone 5. The refresh rate is higher tho.
It has worse USB-C connectivity as well, the Fairphone 6 has just USB 2.0 (!!!!) compared to 3.0 on the Fairphone 5.
They also got rid of the sky blue color (which was the prettiest imo) and of the transparent option.
I don’t really understand Qualcomm processors, but at least the new GPU seems to have a better benchmark score?
#Fairphone #Fairphone5 #Fairphone6

Palestinians struggle to get donated food at a community kitchen, in Gaza City, northern Gaza Strip, July 26, 2025.
Photo by Abdel Kareem Hana/AP
https://abcnews.go.com/International/idf-conduct-aid-airdrops-gaza-hunger-crisis…

"‘In rare triumph, camera traps snap endangered wildcats in Pakistan"
#Pakistan #Animals #Wildcat

In rare triumph, camera traps snap endangered wildcats in Pakistan
Conservationists snapped images of two small wildcat species in Pakistan earlier this year: an Asiatic caracal (Caracal caracal schimitzi) and a sand cat (Felis margarita) — both which are incredibly rare in the country. Information on both cats in Pakistan is limited, with the sand cat presumed possibly extinct there, according to the IUCN, the […]

Hey has anyone seen– *click* oh there you are! 🐈‍⬛

Since announcing our plan to launch
Liberty Vans
equipped with chaplains, lawyers, veterans, and camera crews
to follow ICE raids in real time and expose them to the world,
we’ve seen an outpouring of support from every corner of the country.
We’ve had supporters step up from ALL 50 STATES.
People are ready to fight back and shine a light on the Trump administration's abuse of our country.
We set a goal to raise $1,000,000 to fund the vans, the …

I just gave to the Save America Movement!
Join the fight »

Super busy week, but here's some #FootpathFriday for you (from our amazing sunset solstice hike last Saturday), along a ridge which is part of the DE/AT borderline... 😍
#LandscapePhotography

Yay it’s #Caturday

Today has been mainly about stripping down my favourite mountain bike for repainting and renovation.
#BikeTooter

what are your thoughts on this camera ?
#samsung #camera #PL210

Dear old Violet.
She'll be turning 13 in October, so she's kind of on borrowed time for a greyhound. She seems to have lost most of her vision now and is underweight, though her appetite is still huge and she still loves her walks.
She was once a terror for the local cats and squirrels but now if they remain still she doesn't spot them. She still sniffs every place that she remembers them to have been.

Cooper’s Hawk (immature). LA Arboretum, Arcadia, California, USA. June, 2025. #laarboretum #hawk #coopershawk

🇺🇦 #NowPlaying on BBCRadio3's #Breakfast
Giovanni Battista Vitali, Alessandro Andiani, Claudio Andriani & Italico Splendore:
🎵 Sonate da camera, Op. 14 (Excerpts Arr. for Chamber Ensemble): Suite No. 3
https://open.spotify.com/track/0S2Vc5HlvMh351dsK2k6Qc

I burned pictures on a CD today! Inside the camera I was using to take the pictures!
Because the early 2000s had cool tech shit like that, unlike the endless barrage of mostly black surveillance rectangles of today.

i'm finna hike up to the used record store and see if i can sell some records
Machine-generated ALT: three photos showcase a collection of 12 diverse vinyl records, spanning genres such as rock, soul, jazz, Christmas music, and contemporary pop, featuring artists like Lucinda Williams, Frank Sinatra, Chick Corea, Ramsey Lewis, Lana Del Rey, Mavis Staples, and Hugh Masekela.

Series C, Episode 10 - Ultraworld
TARRANT: And because they said it we're supposed to believe them.
AVON: What else are we to believe? I told you they could take us out like that. [snaps fingers] Why should they bother to lie?
[Tarrant exits]
https://blake.torpidity.net/m/310/256

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

The thermal camera effect on the Apple Event invite is the strongest indication yet that Craig Federighi will be facing-off against a Predator.

Black Camera Close-Up on Sinners (2025): Critical Approaches to Ryan Coogler’s Groundbreaking Black Vampiric Horror Film
https://ift.tt/cgtz0wv
updated: Thursday, June 26, 2025 - 9:17amfull name / name of organization: Black Camera Special…
via Input 4 RELCFP

Wonderfully geeky look into capturing awesome train photographs with a linear slit camera setup. The best part is all the details about the post processing steps.
https://daniel.lawrence.lu/blog/y2025m09d21/

Line scan camera image processing
I use my line scan camera to take cool pictures of trains and other stuff.

Google Pixel 10 review: justifies its price better than the Pixel 9 with upgrades like a triple camera system and Qi2 support, but it's not a gaming powerhouse (Derrek Lee/Android Central)
https://www.androidcentral.com/phones/google-pixel-10-review

The Google Pixel 10 is the upgrade I was hoping for
Google put more magic into the Pixel 10, and it's really starting to feel like AI is finding its moment.

PriorFormer: A Transformer for Real-time Monocular 3D Human Pose Estimation with Versatile Geometric Priors
Mohamed Adjel (LAAS-GEPETTO), Vincent Bonnet (IPAL, LAAS-GEPETTO, CNRS-AIST JRL)
https://arxiv.org/abs/2508.18238

PriorFormer: A Transformer for Real-time Monocular 3D Human Pose Estimation with Versatile Geometric Priors
This paper proposes a new lightweight Transformer-based lifter that maps short sequences of human 2D joint positions to 3D poses using a single camera. The proposed model takes as input geometric priors including segment lengths and camera intrinsics and is designed to operate in both calibrated and uncalibrated settings. To this end, a masking mechanism enables the model to ignore missing priors during training and inference. This yields a single versatile network that can adapt to different d…

Aww, Serge Fiori died: https://vancouver.citynews.ca/2025/06/24/quebec-singer-songwriter-serge-fiori-founder-of-rock-group-harmonium-dead-at-73/
That name won’t mean anything except to Canadians o…

Quebec singer Serge Fiori dead at 73
Quebec singer-songwriter Serge Fiori, founder of French-Canadian rock band Harmonium, died Tuesday at the age of 73.

#caturday #CatsOMastodon
Teddy is protecting the household from an invasion of tea towels.

A very cool thread about live audio for video from @…
#gearsquad
https://old.mermaid…

Breaking another presidential norm, Trump drops the f-bomb on camera : NPR
https://www.npr.org/2025/06/24/nx-s1-5443337/trump-expletive-israel-iran

The perfect killing machine doesn’t exist.... https://www.theverge.com/news/708481/microsoft-teams-mercedes-benz-integration-in-car-camera-support

Mercedes-Benz will let you use an in-car camera in Microsoft Teams while driving
Mercedes-Benz is the first car maker to allow its in-car camera to work in Microsoft Teams meetings while you’re driving. It’s coming to the all-new CLA first.

👀 This 1D camera captures 2D images of things it can’t see
#camera

This 1D camera captures 2D images of things it can’t see | Arduino Blog
Yes, the title of this article sounds pretty crazy. But not only is it entirely possible through the lens of physics, but it is also practical to achieve in the real world using affordable parts. Jon Bumstead pulled it off with an Arduino, a photoresistor, and an inexpensive portable projector. Today’s digital camera sensors are […]

New method for subtraction of common background fluctuation for radio camera: Chunked Principal Component Analysis method
Pranshu Mandal, Tomu Nitta, Makoto Nagai, Nario Kuno
https://arxiv.org/abs/2508.16155

New method for subtraction of common background fluctuation for radio camera: Chunked Principal Component Analysis method
We present a new algorithm, ChunkedPCA, to remove common background fluctuations from datasets acquired with a radio camera. ChunkedPCA is an improvement on using PCA to achieve fewer artifacts and better RMS on the cleaned dataset. The proposed algorithm determines the background fluctuation by grouping the detector pixels not used in the direct observation of the source. This group is then used to get the background fluctuation for that time and used to subtract the background from the data o…

Enabled #syncthing from my phone to the #Turris. Syncthing-fork from F-Droid https://f-droid.org/en/packages/com.gi

SPT-3G D1: CMB temperature and polarization power spectra and cosmology from 2019 and 2020 observations of the SPT-3G Main field
E. Camphuis, W. Quan, L. Balkenhol, A. R. Khalife, F. Ge, F. Guidi, N. Huang, G. P. Lynch, Y. Omori, C. Trendafilova, A. J. Anderson, B. Ansarinejad, M. Archipley, P. S. Barry, K. Benabed, A. N. Bender, B. A. Benson, F. Bianchini, L. E. Bleem, F. R. Bouchet, L. Bryant, M. G. Campitiello, J. E. Carlstrom, C. L. Chang, P. Chaubal, P. M. Chichura, A. Chokshi, T.…

SPT-3G D1: CMB temperature and polarization power spectra and cosmology from 2019 and 2020 observations of the SPT-3G Main field
We present measurements of the temperature and E-mode polarization angular power spectra of the cosmic microwave background (CMB) from observations of 4% of the sky with SPT-3G, the current camera on the South Pole Telescope (SPT). The maps used in this analysis are the deepest used in a CMB TT/TE/EE analysis to date. The maps and resulting power spectra have been validated through blind and unblind tests. The measurements of the lensed EE and TE spectra are the most precise to date at l=1800-4…

An American dipper, Cinclus mexicanus, living up to its name at Snow Lake earlier this week. These guys are aquatic songbirds, basically thrushes who saw what ducks do and decided it looked fun
#naturalist #wildlife #bird

🇺🇦 #NowPlaying on KEXP's #MiddayShow
Camera Obscura:
🎵 Lloyd, I’m Ready to Be Heartbroken
#CameraObscura
https://cameraobscuramusic.bandcamp.com/album/lloyd-im-ready-to-be-heartbroken
https://open.spotify.com/track/52PuLmsxTDOI2WAqpzYjoT

A Joint JWST and HST View of Omega Centauri: Multiple Stellar Populations and Their Kinematics
T. Ziliotto, A. P. Milone, G. Cordoni, A. F. Marino, M. V. Legnardi, E. Dondoglio, E. Bortolan, F. Muratore
https://arxiv.org/abs/2506.21187

A Joint JWST and HST View of Omega Centauri: Multiple Stellar Populations and Their Kinematics
We combine F115W and F277W images collected with the Near Infrared Camera of the James Webb Space Telescope (JWST) with multi-band, multi-epoch Hubble Space Telescope (HST) observations of Omega Centauri to investigate its multiple stellar populations and internal kinematics. Our study focuses on a region spanning $\sim$0.9 to $\sim$2.3 half-light radii from the cluster center, largely unexplored by HST and JWST. Using chromosome maps, we identify the principal populations along the upper main …

Pixel 10 gets a 10.8 MP telephoto lens; 10 Pro and Pro XL get an AI-driven Pro Res Zoom capable of up to 100x zoom; all models get AI features like Camera Coach (Damien Wilde/9to5Google)
https://9to5google.com/2025/08/20/pixel-10-camera-features/

Pixel 10 camera adds ‘Camera Coach’, 100x ‘Pro Res Zoom’ 24fps video, plus more new features
The Pixel 10 series has officially been unveiled with new camera features and upgrades for existing functions. Here's what you need to know.

On the Particle Image Overlap in Single Camera Defocusing Approaches
Christian Sax, Jochen Kriegseis
https://arxiv.org/abs/2506.18170 https://

On the Particle Image Overlap in Single Camera Defocusing Approaches
Particle image (PI) overlap presents a significant challenge in single-camera particle tracking and sizing techniques such as Defocusing Particle Tracking Velocimetry (DPTV) and Interferometric Particle Imaging (IPI). In DPTV, overlap obscures PI boundaries, complicating the detection and accurate estimation of PI diameter and center position, which increases uncertainty in the reconstructed particle positions. In IPI, overlap reduces the usable area of the interference pattern, limiting the ac…

\textsc{T-Mask}: Temporal Masking for Probing Foundation Models across Camera Views in Driver Monitoring
Thinesh Thiyakesan Ponbagavathi, Kunyu Peng, Alina Roitberg
https://arxiv.org/abs/2508.16207

\textsc{T-Mask}: Temporal Masking for Probing Foundation Models across Camera Views in Driver Monitoring
Changes of camera perspective are a common obstacle in driver monitoring. While deep learning and pretrained foundation models show strong potential for improved generalization via lightweight adaptation of the final layers ('probing'), their robustness to unseen viewpoints remains underexplored. We study this challenge by adapting image foundation models to driver monitoring using a single training view, and evaluating them directly on unseen perspectives without further adaptation. We benchma…

Welfare check? Bloody hell!
#NSWpolice

Body-worn camera footage shown in court after woman accuses NSW Police of assault, battery
Body-worn camera footage has shown the moment a woman was pepper sprayed and her dog tasered during a mental health welfare check by NSW Police.

The ref cam is also stupid. The perspective is way too distant and the jostling of video on a running human without stabilizing technology is too ridiculous to actually show anything.
PGMOL can’t even get VAR right with umpteen HD replays, so maybe they’re happy to have a ragged replay as a face-saving charade.
If it was accurately synced to what Simon Hooper saw, large sections of the game would be blank screens. He’s hopeless. I don’t need a camera affixed to his chest to see t…

#Blakes7 Series C, Episode 13 - Terminal
AVON: Thank you.
TARRANT: Avon, are we still on route for Calipheron? Are we?
AVON: No.
TARRANT: You've changed course?
AVON: Obviously.
TARRANT: You had no right to do that.

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Designing across domains with declarative thinking: Insights from the 96-Eyes ptychographic imager project
Antony C Chan
https://arxiv.org/abs/2508.18512 https://

Designing across domains with declarative thinking: Insights from the 96-Eyes ptychographic imager project
This article presents a practitioner's reflection on applying declarative, 5th generation, problem formulation language (5GL) to de novo imaging system design, informed by experiences across the interdisciplinary research in academia and cross-functional product development within the private sector. Using the 96-Eyes project: 96-camera parallel multi-modal imager for high-throughput drug discovery as a representative case, I illustrate how project requirements, ranging from hardware constraint…

Please consider supporting Sofia's Camera Club ride for pancreatic cancer up Cypress https://cypresschallenge.ca/team/scc This will be our 8th year. @… join…

Time to feed the baby 🐈

Simulation for Noncontact Radar-Based Physiological Sensing Using Depth-Camera-Derived Human 3D Model with Electromagnetic Scattering Analysis
Kimitaka Sumi, Takuya Sakamoto
https://arxiv.org/abs/2507.13826

Simulation for Noncontact Radar-Based Physiological Sensing Using Depth-Camera-Derived Human 3D Model with Electromagnetic Scattering Analysis
This study proposes a method for simulating signals received by frequency-modulated continuous-wave radar during respiratory monitoring, using human body geometry and displacement data acquired via a depth camera. Unlike previous studies that rely on simplified models of body geometry or displacement, the proposed approach models high-frequency scattering centers based on realistic depth-camera-measured body shapes and motions. Experiments were conducted with six participants under varying cond…

Clearly at least the vandals (aka drivers) knew about it.
'Public should have been told about North Yorkshire speed camera'
https://www.bbc.com/news/articles/ckg57gle8l1o
> The fixed camera on the A64, near Malton, was vandalised hours before it was due to be…

"The camera does not like acting. The camera is only interested in filming behaviour. So you damn well learn your lines until you know them inside out, while standing on your head!"
—Ben Kingsley
#acting #coaching

The camera angle is so high in the air.
#nwsl

The First Photos from the BIGGEST Camera Ever Made: #Rubin

As federal immigration agents attacked a U.S. citizen, they warned him:
“You’ve got no rights here.”
What began as a simple traffic stop for Kenny Laynez-Ambrosio, an 18-year-old Floridian, in May,
turned into a traumatizing arrest when U.S. Customs and Border Protection arrived at the scene.
Alongside his mother and two undocumented male companions,
Laynez-Ambrosio was laughed at, ridiculed, and violently detained by a group of officers,
according to vide…

Immigration Agents Laugh at U.S. Citizen as He Records His Own Arrest
Kenny Laynez-Ambrosio, 18, turned on his camera as immigration agents arrested him—after he told them he’s a U.S. citizen.

I missed #SilentSunday yesterday, and so I’ll post this tiny, little toadstool here as a #MondayMushroom instead.

PneuGelSight: Soft Robotic Vision-Based Proprioception and Tactile Sensing
Ruohan Zhang (University of Illinois, Urbana-Champaign, USA), Uksang Yoo (Carnegie Mellon University, USA), Yichen Li (Carnegie Mellon University, USA), Arpit Argawal (Carnegie Mellon University, USA), Wenzhen Yuan (University of Illinois, Urbana-Champaign, USA)
https://

PneuGelSight: Soft Robotic Vision-Based Proprioception and Tactile Sensing
Soft pneumatic robot manipulators are popular in industrial and human-interactive applications due to their compliance and flexibility. However, deploying them in real-world scenarios requires advanced sensing for tactile feedback and proprioception. Our work presents a novel vision-based approach for sensorizing soft robots. We demonstrate our approach on PneuGelSight, a pioneering pneumatic manipulator featuring high-resolution proprioception and tactile sensing via an embedded camera. To opt…

The largest digital camera ever built has released its first shots of the universe (Adithi Ramakrishnan/Associated Press)
https://apnews.com/article/vera-rubin-observatory-nsf-d7b645d2b1c0caad16f0945e1227a9b4
http://www.memeorandum.com/250623/p98#a250623p98

> Ever wonder why you never see a smartphone photo printed and framed on the wall? I'll explain exactly why.
The photos above look similar at a glance, but there are some key differences that seem small but are actually very sensitive to our perception of humans
https://candid9.com/phone-camera/…

oooh Rosey Maple Moth emerged
#moth

Sometimes I'm silly. Noticed that a fire camera I was watching showed a clock over a minute ahead of my system time, assumed the problems was me. Installed Chrony (Linux Mint, recent Win convert so I'm hardly a power user) and spent the usual 20 minutes farting around with it. Couldn't seem to get it right.
Finally realized my clock IS within a handful of microseconds of the NTP server; it's the clock on the camera that's wrong. D'oh.

Headlines and images don't have to be distressing:

Headlines and images don't have to be distressing:

California Cops Investigate ‘Immigration Protest’ With AI-Camera System https://www.404media.co/california-cops-investigate-immigration-protest-with-ai-camera-system/

Dark Areas ⬛️
黑黢黢的角落 ⬛️
📷 Nikon FE
🎞️Ilford FP4 Plus, expired 1994
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Here's Nº 31 Zoraida Icabalceta from IC's Bombers Turning a Corner and the back Side of Nº 11 June Dickson -- College sports is starting up again and I'm looking forward to seeing some Soccer games and developing Cornell Basketball shots from last Winter while waiting for the season to start
#photo

House Finch collecting cactus fuzz for its nest. Huntington Library, San Marino, California, USA. June, 2025. #huntingtonlibrary #bird #birds

Can we make NeRF-based visual localization privacy-preserving?
Maxime Pietrantoni, Martin Humenberger, Torsten Sattler, Gabriela Csurka
https://arxiv.org/abs/2508.18971 https://…

Can we make NeRF-based visual localization privacy-preserving?
Visual localization (VL) is the task of estimating the camera pose in a known scene. VL methods, a.o., can be distinguished based on how they represent the scene, e.g., explicitly through a (sparse) point cloud or a collection of images or implicitly through the weights of a neural network. Recently, NeRF-based methods have become popular for VL. While NeRFs offer high-quality novel view synthesis, they inadvertently encode fine scene details, raising privacy concerns when deployed in cloud-bas…

An H$\alpha$ Cloud in the HI Tail: Recent Star Formation in the Outskirts of NGC 4258 Revealed by Nanshan 1-m Telescope
Cheng Cheng, Jia-Sheng Huang, Peng Wei, Ali Esamdin, Guojie Feng, Zhi-Xiang Zhang, Haojing Yan, Wei Du, Pei Zuo, Zi-Jian Li, Gustavo Orellana, Letian Wang, Yong Wang, Abdusamatjan Iskandar, Shahidin Yaqup
https://

An H$α$ Cloud in the HI Tail: Recent Star Formation in the Outskirts of NGC 4258 Revealed by Nanshan 1-m Telescope
We present first-light deep H$α$ imaging taken with the Nanshan 1-meter wide-field telescope on the local galaxy NGC 4258, alongside archival data from Hubble Space telescope (HST), Westerbork Synthesis Radio Telescope, and The Dark Energy Camera Legacy Survey. The H$α$ image shows ongoing star formation not only inside the galaxy but also in an HI cloud in the eastern HI tail, which is roughly 16 kpc away from the main galaxy. The HST images reveal several ultra-blue compact objects ($\rm F5…

Uncertainties of a Spherical Magnetic Field Camera
Fynn Foerger, Philip Suskin, Marija Boberg, Jonas Faltinath, Tobias Knopp, Martin M\"oddel
https://arxiv.org/abs/2506.17359

Uncertainties of a Spherical Magnetic Field Camera
Spherical harmonic expansions are well-established tools for estimating magnetic fields from surface measurements and are widely used in applications such as tomographic imaging, geomagnetism, and biomagnetism. Although the mathematical foundations of these expansions are well understood, the impact of real-world imperfections, on the uncertainty of the field model has received little attention. In this work, we present a systematic uncertainty propagation analysis for a magnetic field camera t…

The #Caturday is requesting food.
This is what he does

Behold the Very First Color Photograph (1861): Taken by Scottish Physicist & Poet James Clerk Maxwell
https://flip.it/ZdV70o

Behold the Very First Color Photograph (1861): Taken by Scottish Physicist & Poet James Clerk Maxwell
Since its ancient origins as the camera obscura, the photographic camera has always mimicked the human eye, allowing light to enter an aperture, then projecting an image upside down. Renaissance artists relied on the camera obscura to sharpen their own visual perspectives.

Radar and Event Camera Fusion for Agile Robot Ego-Motion Estimation
Yang Lyu, Zhenghao Zou, Yanfeng Li, Chunhui Zhao, Quan Pan
https://arxiv.org/abs/2506.18443

Radar and Event Camera Fusion for Agile Robot Ego-Motion Estimation
Achieving reliable ego motion estimation for agile robots, e.g., aerobatic aircraft, remains challenging because most robot sensors fail to respond timely and clearly to highly dynamic robot motions, often resulting in measurement blurring, distortion, and delays. In this paper, we propose an IMU-free and feature-association-free framework to achieve aggressive ego-motion velocity estimation of a robot platform in highly dynamic scenarios by combining two types of exteroceptive sensors, an even…

GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations
Fadi Khatib, Dror Moran, Guy Trostianetsky, Yoni Kasten, Meirav Galun, Ronen Basri
https://arxiv.org/abs/2508.18242

GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations
We introduce GSVisLoc, a visual localization method designed for 3D Gaussian Splatting (3DGS) scene representations. Given a 3DGS model of a scene and a query image, our goal is to estimate the camera's position and orientation. We accomplish this by robustly matching scene features to image features. Scene features are produced by downsampling and encoding the 3D Gaussians while image features are obtained by encoding image patches. Our algorithm proceeds in three steps, starting with coarse m…

📸 srRAW 1.2 Is a Professional Cinema Camera Inside the iPhone
https://petapixel.com/2025/07/31/srraw-1-2-is-a-professional-cinema-camera-inside-the-iphone/

srRAW 1.2 Is a Professional Cinema Camera Inside the iPhone
A full-fledged cinema camera experience on iPhone.

Sifting for a Stream: The Morphology of the $300S$ Stellar Stream
Benjamin Cohen, Alexander P. Ji, Peter S. Ferguson, Sergey E. Koposov, Alex Drlica-Wagner, Andrew P. Li, Ting S. Li, Lara R. Cullinane, Gary S. Da Costa, Denis Erkal, Kyler Kuehn, Geraint F. Lewis, Sarah L. Martell, Andrew B. Pace, Daniel B. Zucker, Petra Awad, Joss Bland-Hawthorn, Guilherme Limberg, Clara E. Mart\'inez-V\'azquez, Joshua D. Simon, Yong Yang

Sifting for a Stream: The Morphology of the $300S$ Stellar Stream
Stellar streams are sensitive laboratories for understanding the small-scale structure in our Galaxy's gravitational field. Here, we analyze the morphology of the $300S$ stellar stream, which has an eccentric, retrograde orbit and thus could be an especially powerful probe of both baryonic and dark substructures within the Milky Way. Due to extensive background contamination from the Sagittarius stream (Sgr), we perform an analysis combining Dark Energy Camera Legacy Survey photometry, $\textit…

Hands-on with iOS 26: Liquid Glass is impressive but can also be distracting, Camera redesign is solid, Call Filtering feature in the Phone app is great, more (Dan Moren/Six Colors)
https://sixcolors.com/post/2025/07/first-look-ios-26-public-beta/

First Look: iOS 26 Public Beta
iOS 26! It feels like just last year we were here discussing iOS 18. How time flies. After a year that saw the debut of Apple Intelligence and the subsequent controversy over the features that it d…

Improvement on LiDAR-Camera Calibration Using Square Targets
Zhongyuan Li, Honggang Gou, Ping Li, Jiaotong Guo, Mao Ye
https://arxiv.org/abs/2506.18294 htt…

Improvement on LiDAR-Camera Calibration Using Square Targets
Precise sensor calibration is critical for autonomous vehicles as a prerequisite for perception algorithms to function properly. Rotation error of one degree can translate to position error of meters in target object detection at large distance, leading to improper reaction of the system or even safety related issues. Many methods for multi-sensor calibration have been proposed. However, there are very few work that comprehensively consider the challenges of the calibration procedure when appli…

Bo Burnham once said:
“Why do you rich fucking white people Insist on seeing every socio-political conflict through the myopic lens of your own self-actualization? This isn't about you. So either get with it, or get out of the fucking way”

For the first time, a team at Western University in collaboration with the Defence Research and Development Canada has used a satellite-tracking camera system to monitor #satellites over the high Arctic: https://spaceq.ca/meteor-tracking-camera-tech-used-to-track-satellites-in-the-high-arctic/

Learning-Based Distance Estimation for 360{\deg} Single-Sensor Setups
Yitong Quan, Benjamin Kiefer, Martin Messmer, Andreas Zell
https://arxiv.org/abs/2506.20586

Learning-Based Distance Estimation for 360° Single-Sensor Setups
Accurate distance estimation is a fundamental challenge in robotic perception, particularly in omnidirectional imaging, where traditional geometric methods struggle with lens distortions and environmental variability. In this work, we propose a neural network-based approach for monocular distance estimation using a single 360° fisheye lens camera. Unlike classical trigonometric techniques that rely on precise lens calibration, our method directly learns and infers the distance of objects from …

SoccerNet 2025 Challenges Results
Silvio Giancola, Anthony Cioppa, Marc Guti\'errez-P\'erez, Jan Held, Carlos Hinojosa, Victor Joos, Arnaud Leduc, Floriane Magera, Karen Sanchez, Vladimir Somers, Artur Xarles, Antonio Agudo, Alexandre Alahi, Olivier Barnich, Albert Clap\'es, Christophe De Vleeschouwer, Sergio Escalera, Bernard Ghanem, Thomas B. Moeslund, Marc Van Droogenbroeck, Tomoki Abe, Saad Alotaibi, Faisal Altawijri, Steven Araujo, Xiang Bai, Xiaoyang Bi, Jiawang Cao, …

SoccerNet 2025 Challenges Results
The SoccerNet 2025 Challenges mark the fifth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in football video understanding. This year's challenges span four vision-based tasks: (1) Team Ball Action Spotting, focused on detecting ball-related actions in football broadcasts and assigning actions to teams; (2) Monocular Depth Estimation, targeting the recovery of scene geometry from single-camera broadcast clips through relative depth est…

Reproducible Evaluation of Camera Auto-Exposure Methods in the Field: Platform, Benchmark and Lessons Learned
Olivier Gamache, Jean-Michel Fortin, Mat\v{e}j Boxan, Fran\c{c}ois Pomerleau, Philippe Gigu\`ere
https://arxiv.org/abs/2506.18844

Reproducible Evaluation of Camera Auto-Exposure Methods in the Field: Platform, Benchmark and Lessons Learned
Standard datasets often present limitations, particularly due to the fixed nature of input data sensors, which makes it difficult to compare methods that actively adjust sensor parameters to suit environmental conditions. This is the case with Automatic-Exposure (AE) methods, which rely on environmental factors to influence the image acquisition process. As a result, AE methods have traditionally been benchmarked in an online manner, rendering experiments non-reproducible. Building on our prior…

🌌 The World’s Largest Camera Captures 10 Million Galaxies, Discovers 2,104 Asteroids in First Photos
https://petapixel.com/2025/06/23/the-worlds-largest-camera-captures-10-million-galaxies-discovers-2104-astero…

The World's Largest Camera's First Photo: 5 Gigapixels Showing 10 Million Galaxies
One of humanity's greatest achievements.

IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals
Markus Gross, Aya Fahmy, Danit Niwattananan, Dominik Muhle, Rui Song, Daniel Cremers, Henri Mee{\ss}
https://arxiv.org/abs/2506.20671

IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals
Semantic Scene Completion (SSC) has emerged as a pivotal approach for jointly learning scene geometry and semantics, enabling downstream applications such as navigation in mobile robotics. The recent generalization to Panoptic Scene Completion (PSC) advances the SSC domain by integrating instance-level information, thereby enhancing object-level sensitivity in scene understanding. While PSC was introduced using LiDAR modality, methods based on camera images remain largely unexplored. Moreover, …

🪩 DJI takes on the 360 action camera market with the Osmo 360
https://www.dpreview.com/news/1316046707/dji-takes-on-the-360-action-camera-market-with-the-osmo-360

YouTube gives Shorts creators access to new generative AI features powered by Veo 2, including an image-to-video tool and new effects (Aisha Malik/TechCrunch)
https://techcrunch.com/2025/07/23/youtube-shorts-is-adding-an-image-to-video-ai-…

YouTube Shorts is adding an image-to-video AI tool, new AI effects | TechCrunch
The image to video feature lets creators turn a picture from their camera roll into a a six-second video.

G2S-ICP SLAM: Geometry-aware Gaussian Splatting ICP SLAM
Gyuhyeon Pak, Hae Min Cho, Euntai Kim
https://arxiv.org/abs/2507.18344 https://arxiv.org/pdf/2507.…

G2S-ICP SLAM: Geometry-aware Gaussian Splatting ICP SLAM
In this paper, we present a novel geometry-aware RGB-D Gaussian Splatting SLAM system, named G2S-ICP SLAM. The proposed method performs high-fidelity 3D reconstruction and robust camera pose tracking in real-time by representing each scene element using a Gaussian distribution constrained to the local tangent plane. This effectively models the local surface as a 2D Gaussian disk aligned with the underlying geometry, leading to more consistent depth interpretation across multiple viewpoints comp…

Black and white shot of a Zinnia in soft focus -- gotta be the 7Aristans 50mm/0.95 because it didn't identify itself to the camera
#photo #photography #flowers

Multi-perspective monitoring of wildlife and human activities from camera traps and drones with deep learning models
Hao Chen, Fang Qiu, Li An, Douglas Stow, Eve Bohnett, Haitao Lyu, Shuang Tian
https://arxiv.org/abs/2508.15629

Multi-perspective monitoring of wildlife and human activities from camera traps and drones with deep learning models
Wildlife and human activities are key components of landscape systems. Understanding their spatial distribution is essential for evaluating human wildlife interactions and informing effective conservation planning. Multiperspective monitoring of wildlife and human activities by combining camera traps and drone imagery. Capturing the spatial patterns of their distributions, which allows the identification of the overlap of their activity zones and the assessment of the degree of human wildlife c…

Inside the Vera C. Rubin Observatory, whose 3.2-gigapixel camera will produce 60PB of space image data over 10 years, to be analyzed using ML and deep learning (New York Times)
https://www.nytimes.com/2025/06/20/science…

How Vera Rubin Telescope Scientists Will Deal With 60 Million Billion Bytes of Imagery
The Vera C. Rubin Observatory will make the study of stars and galaxies more like the big data-sorting exercises of contemporary genetics and particle physics.

Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy
Tianyi Zhang, Haonan Duan, Haoran Hao, Yu Qiao, Jifeng Dai, Zhi Hou
https://arxiv.org/abs/2508.13103

Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy
Vision-Language-Action (VLA) models frequently encounter challenges in generalizing to real-world environments due to inherent discrepancies between observation and action spaces. Although training data are collected from diverse camera perspectives, the models typically predict end-effector poses within the robot base coordinate frame, resulting in spatial inconsistencies. To mitigate this limitation, we introduce the Observation-Centric VLA (OC-VLA) framework, which grounds action predictions…

G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration
Ramil Khafizov, Artem Komarichev, Ruslan Rakhimov, Peter Wonka, Evgeny Burnaev
https://arxiv.org/abs/2508.11379

G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration
We introduce G-CUT3R, a novel feed-forward approach for guided 3D scene reconstruction that enhances the CUT3R model by integrating prior information. Unlike existing feed-forward methods that rely solely on input images, our method leverages auxiliary data, such as depth, camera calibrations, or camera positions, commonly available in real-world scenarios. We propose a lightweight modification to CUT3R, incorporating a dedicated encoder for each modality to extract features, which are fused wi…

RoboRetriever: Single-Camera Robot Object Retrieval via Active and Interactive Perception with Dynamic Scene Graph
Hecheng Wang, Jiankun Ren, Jia Yu, Lizhe Qi, Yunquan Sun
https://arxiv.org/abs/2508.12916

RoboRetriever: Single-Camera Robot Object Retrieval via Active and Interactive Perception with Dynamic Scene Graph
Humans effortlessly retrieve objects in cluttered, partially observable environments by combining visual reasoning, active viewpoint adjustment, and physical interaction-with only a single pair of eyes. In contrast, most existing robotic systems rely on carefully positioned fixed or multi-camera setups with complete scene visibility, which limits adaptability and incurs high hardware costs. We present \textbf{RoboRetriever}, a novel framework for real-world object retrieval that operates using …

RCDINO: Enhancing Radar-Camera 3D Object Detection with DINOv2 Semantic Features
Olga Matykina, Dmitry Yudin
https://arxiv.org/abs/2508.15353 https://arxiv…

RCDINO: Enhancing Radar-Camera 3D Object Detection with DINOv2 Semantic Features
Three-dimensional object detection is essential for autonomous driving and robotics, relying on effective fusion of multimodal data from cameras and radar. This work proposes RCDINO, a multimodal transformer-based model that enhances visual backbone features by fusing them with semantically rich representations from the pretrained DINOv2 foundation model. This approach enriches visual representations and improves the model's detection performance while preserving compatibility with the baseline…

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
Chin-Yang Lin, Cheng Sun, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Yu-Lun Liu
https://arxiv.org/abs/2508.14041

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift, inaccurate geometry initialization, and severe memory limitations. To address these issues, we introduce LongSplat, a robust unposed 3D Gaussian Splatting framework featuring: (1) Incremental Joint Optimization that concurrently optimizes camera poses and 3D Gau…

EgoPrivacy: What Your First-Person Camera Says About You?
Yijiang Li, Genpei Zhang, Jiacheng Cheng, Yi Li, Xiaojun Shan, Dashan Gao, Jiancheng Lyu, Yuan Li, Ning Bi, Nuno Vasconcelos
https://arxiv.org/abs/2506.12258

EgoPrivacy: What Your First-Person Camera Says About You?
While the rapid proliferation of wearable cameras has raised significant concerns about egocentric video privacy, prior work has largely overlooked the unique privacy threats posed to the camera wearer. This work investigates the core question: How much privacy information about the camera wearer can be inferred from their first-person view videos? We introduce EgoPrivacy, the first large-scale benchmark for the comprehensive evaluation of privacy risks in egocentric vision. EgoPrivacy covers t…

Iterative Camera-LiDAR Extrinsic Optimization via Surrogate Diffusion
Ni Ou, Zhuo Chen, Xinru Zhang, Junzheng Wang
https://arxiv.org/abs/2506.14706 https:/…

Iterative Camera-LiDAR Extrinsic Optimization via Surrogate Diffusion
Cameras and LiDAR are essential sensors for autonomous vehicles. The fusion of camera and LiDAR data addresses the limitations of individual sensors but relies on precise extrinsic calibration. Recently, numerous end-to-end calibration methods have been proposed; however, most predict extrinsic parameters in a single step and lack iterative optimization capabilities. To address the increasing demand for higher accuracy, we propose a versatile iterative framework based on surrogate diffusion. Th…

CamCloneMaster: Enabling Reference-based Camera Control for Video Generation
Yawen Luo, Jianhong Bai, Xiaoyu Shi, Menghan Xia, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Tianfan Xue
https://arxiv.org/abs/2506.03140

CamCloneMaster: Enabling Reference-based Camera Control for Video Generation
Camera control is crucial for generating expressive and cinematic videos. Existing methods rely on explicit sequences of camera parameters as control conditions, which can be cumbersome for users to construct, particularly for intricate camera movements. To provide a more intuitive camera control method, we propose CamCloneMaster, a framework that enables users to replicate camera movements from reference videos without requiring camera parameters or test-time fine-tuning. CamCloneMaster seamle…