There are many single great idea people. While they looks super smart (and the idea is great), but often they are not as smart as they look. That's a 10-15 years observation.

Great thread about great paper figures

Last week we launched IMC2025-Ongoing on @kaggle.com The dataset is exactly as in IMC2025, but the competition is on-going for a year, making it better for academic leaderboard and persistency. kaggle.com/competitions... 1/2

Why are you in 🦋? (I'm) For the same reason I downloaded: 1. WhatsApp 2. Signal, used only when living in 🇳🇱. 3. Telegram (in such order) to be in contact with someone/someppl The 🐦 still offers better UX for me. Nevertheless, Kudos to all folks engaged on making a clear blue sky 💪🏼

Come work with me @slu-official.bsky.social! The Department of Computer Science is running an open rank search with an emphasis on AI and Cybersecurity (although we’ll consider other areas as well for extraordinary candidates). slu.wd5.myworkdayjobs.com/en-US/Career...

🧍‍♀️ Introducing Anny: an open, interpretable, and differentiable human body model for all ages. Grounded in anthropometric data (MakeHuman) & WHO stats, Anny offers: 🧠 Interpretable shape control 👶👩‍🦳 Unified from infants to elders 🧩 Versatile for fitting, synthesis & HMR 🌍 Open under Apache 2.0

Code is out. We provide the pre-trained ACE-G model, as well as code to replicate the paper results, and to evaluate ACE-G on new scenes. #ICCV2025 github.com/nianticspati...

Between yesterday and today, there has been submitted at least 60 CVPR Workshop proposals.

Hello, a PSA. Arxiv is the server that many academics use to discuss their work before it is peer reviewed. It is widely viewed as a blessing.

Great overview of the workshops and tutorials. My favorites: 1) CAD representation 2) synthetic data to help city-scale reconstruction 3) trends in 3D vision 4) visual chain-of-thoughts?

I HATE long @bsky.app name-handles. Common, exclude them from the char limit, or whatever. On twitter, when authors are on platform, it means MORE space. Here is means LESS space It is easy to fit the paper name + authors (handles) + tl;dr + arXiv link on twitter, but almost impossible here :(

Scaling Image Geo-Localization to Continent Level Philipp Lindenberger @pesarlin.bsky.social @janhosang.bsky.social Matteo Balice @marcpollefeys.bsky.social Simon Lynen, Eduard Trulls tl;dr: combine ground+aerial to get cell-prototype. Acc@ 42Gb = ground [email protected] arxiv.org/abs/2510.26795

Instance-Level Composed Image Retrieval @billpsomas.bsky.social George Retsinas @nikos-efth.bsky.social Panagiotis Filntisis,Yannis Avrithis, Petros Maragos, Ondrej Chum, @gtolias.bsky.social tl;dr: condition-based retrieval (+dataset) - old photo/sunset/night/aerial/model arxiv.org/abs/2510.25387

The project that started my whitespace obsession... #EMNLP2025 While we've all been worrying about tokenizers, lurking in the background has been the preprocessing *before* tokenization. Poems break standard HTML-to-text linearization systems, and we find that multimodal models aren't a solution.

Epipolar Geometry Improves Video Generation Models Orest Kupyn, Fabian Manhardt, Federico Tombari, Christian Rupprecht tl;dr: Wan->diverse videos->Sampson epipolar error->relative reward signals->Flow-DPO->video generation rankings->3D-consistent videos arxiv.org/abs/2510.21615

Come to our poster this afternoon starting at 2:30 (#214)

All slides for the RANSAC in 2025 tutorial are online #ICCV2025 danini.github.io/ransac-2025-...

Are you at @iccv.bsky.social #ICCV2025? Come by our poster.  📅 October 22, 2025, 14:30 – 16:30 HST  📍 Location: Exhibit Hall I, Poster #207

LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching Aidyn Ubingazhibov, Rémi Pautrat, Iago Suárez, Shaohui Liu, @marcpollefeys.bsky.social , Viktor Larsson tl;dr: Better and faster gluestick with line attention. arxiv.org/abs/2510.16438

Method is named SIMFIT++ due to the criminally underrated SIMFIT by Heinrich stuartheinrich.com/reports/simf...

Slides for my #ICCV2025 RANSAC in 2025 talk are here drive.google.com/file/d/1_1zY...

VibeSAC is here. I will make a separate library a bit later. github.com/ducha-aiki/r...

Take-away messages and Open Problems from RANSAC in 2025 tutorial.

I am starting now at ICCV RANSAC in 2025 Tutorial danini.github.io/ransac-2025-... #ICCV2025

Are you AI optimist or AI pessimist for 3D geometry? @ericbrachmann.bsky.social

Famous black slides from @ericbrachmann.bsky.social --now on differentiable RANSACs

Does RANSAC matter with VGGT? Yes.

Eval of Daniel @danielbarath.bsky.social of SIMFIT++

Inlier threshold estimation

Sota RANSAC by @danielbarath.bsky.social bsky.app/profile/duch...

Minimal Solvers and Model Refinement by @visionviktor #ICCV2025 danini.github.io/ransac-2025-...

Jiri Matas does an intro to RANSAC at "RANSAC in 2025" Tutorial #ICCV2025

Join to my talk in 3 hours at #ICCV2025 to find out the answer (it may surprise you ;) P.S. I am so bad at baiting.... danini.github.io/ransac-2025-...

CroCoDL Workshop at #ICCV, next talk coming up in Room 301B: 13.15 - 13.45: @gabrielacsurka.bsky.social on Privacy Preserving Visual Localization full schedule: buff.ly/kM1Ompf

RANSAC in 2025 is starting now! Room 328. #ICCV2025 @iccv.bsky.social danini.github.io/ransac-2025-...

And the answer is 0.9999 for the win. Lower confidence value always gives you worse results for more or less same runtime. More in our RANSAC Tutorial at #ICCV2025

Trying to mitigate ICCV FOMO today. Staying at home this time. Have fun everybody!

What would you bet on for the RANSAC? a) vibecoded shit in python b) solid C++ library

10th (!!) R6D workshop @ ICCV 2025: cmp.felk.cvut.cz/sixd/worksho... 🤖 Object pose estimation for industrial robotics 📢 Speakers: - Sergey Levine (UC Berkeley) - Haoshu Fang (MIT) - Maximilian Durner (DLR) - Agastya Kalra & Vahe Taamazyan (Intrinsic) 📊 BOP 2025 with new BOP-Industrial datasets

Looking forward to a busy #ICCV2025. I will give three (very different) talks at workshops and tutorials, see info below. We also present two papers, ACE-G and SCR Priors. And it's the 10th (!) anniversary of the R6D workshop, which we co-organize.

Do you trust RANSAC stopping criterion? - Yes, confidence=0.99 FTW - No, max_iter FTW - WTF are you talking about? Answer in comments.

Pro tip: For good Halloween vibes, use non-normalized RoPE on images larger than your training resolution and larger than the composite period of some of the RoPE-rotations. You might get scary ghost structures in your features.

RePoseD: Efficient Relative Pose Estimation With Known Depth Information Yaqing Ding, Viktor Kocur, Václav Vávra, Zuzana Berger Haladová, Jian Yang, @sattlertorsten.bsky.social, Zuzana Kukelova arxiv.org/abs/2501.07742 kocurvik.github.io/reposed/

🌺 Just 4 days to go! Join us in Honolulu for the Instance-Level Recognition and Generation Workshop at #ICCV2025 🏝 🗓️ Oct 19, 8:30am–12:30pm 📍 Room 306 A We’ll have amazing keynotes, plus oral and poster sessions featuring accepted and invited papers. Don’t miss it! ilr-workshop.github.io/ICCVW2025/

Stages of CV research work 1. Denial 2. Anger 3. Bargaining 4. Depression 5. Manual data labeling 6. ??? 7. PROFIT

ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training Leonard Bruns @axelbarroso.bsky.social Tommaso Cavallari, Áron Monszpart, Sowmya Munukutla, Victor Adrian Prisacariu @ericbrachmann.bsky.social tl;dr: SCR=attention(image x map code) arxiv.org/abs/2510.11605

Scene Coordinate Reconstruction Priors @wenjingbian.bsky.social @axelbarroso.bsky.social Tommaso Cavallari, Victor Adrian Prisacariu, @ericbrachmann.bsky.social tl;dr: in title. Depth priors is Laplace around RGBD, and diffusion is point cloud denoising. arxiv.org/abs/2510.12387

HouseTour: A Virtual Real Estate A(I)gent Ata Celen, Marc Pollefeys, Daniel Barath, Iro Armeni tl;dr: 3D trajectory for walkthrough + text summary from 3D reconstruction. openaccess.thecvf.com/content/ICCV...

Cutting the Skip: Training Residual-Free Transformers Yiping Ji et 7 al tl;dr: orthonormal + diagonal init to improve residual-free training. If you need residual-free ViT, use this. Why need though? h/t @pesarlin.bsky.social for pointer. arxiv.org/abs/2510.003...