Recording of the 10th R6D workshop #ICCV2025 w/ results of the 2025 BOP challenge is out: youtu.be/NymS-f4DNh0 3.5h of goodness dedicated to robot-object manipulation w/ Hao-Shu Fang (MIT), Maximilian Durner (DLR), Agastya Kalra+Vahe Taamazyan (Intrinsic) and Sergey Levine (Physical Intelligence)

Of all my multiple Lufthansa flights on this journey, the only one that was punctual was the one with a short connection time, and that I therefore missed due to the previous one being late. Now, after one involuntary overnight stay: delay again. Great job @lufthansagroup.bsky.social

Coarse plan for a 1-week rebuttal period: day 1: read the reviews day 2-6: calm down day 7: write the rebuttal

‼️ Major update to the #ACEZero code base. We added the capabilities of the #ICCV2025 paper on Scene Coordinate Reconstruction Priors. Gives you, e.g., a RGB-D version of ACE0. In the snipped below, I jointly reconstruct multiple RGB-D scans of ScanNet. github.com/nianticlabs/...

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...

Hi everyone. Can we please stop naming methods in leetspeak? It slows down my writing - it is a skill I happily abandoned 20 years ago.

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

After next week, I REALLY need a break from PowerPoint.

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.

Bruns et al., "ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training" Train a scene coordinate regressor with "map codes" (ie, trainable inputs) so that you can train one generalizable regressor. Then, find these "map codes" to localize.

Interested in doing a PhD in machine learning at the University of Edinburgh starting Sept 2026? My group works on topics in vision, machine learning, and AI for climate. For more information and details on how to get in touch, please check out my website: homepages.inf.ed.ac.uk/omacaod

🌟 Scene Coordinate Reconstruction Priors at #ICCV2025 🌟 Can we learn what a successful reconstruction looks like, and use this knowledge when reconstructing new scenes? Explainer: youtu.be/RkV6U5xYc20 Project Page: nianticspatial.github.io/scr-priors Inspiring work by Wenjing Bian et al.!

The #ICCV2025 main conference open access proceedings is up: openaccess.thecvf.com/ICCV2025 Workshop papers will be posted shortly. Aloha!

🔥 ACE-G, the next evolutionary step of ACE at #ICCV2025 🔥 We disentangle coordinate regression and latent map representation which lets us pre-train the regressor to generalize from mapping data to difficult query images. Page: nianticspatial.github.io/ace-g/ Stellar work by Leonard Bruns et al.!

When you present other peoples work with them sitting in the audience.

I think it is a great time to have such a tutorial again. As we see competitive RANSAC-free approaches arise, it is worth looking back - and looking forward.

For those going to @iccv.bsky.social, welcome to our RANSAC tutorial on October 2025 with - Daniel Barath - @ericbrachmann.bsky.social - Viktor Larsson - Jiri Matas - and me danini.github.io/ransac-2025-... #ICCV2025

Whenever I do a voice over, I realize that I sound like Arnold Schwarzenegger when I say "coordinate". Unfortunately, in my line of work, I have to say "coordinate" a lot...

Trendy.

Great to have Kwang on Bluesky! (And quite flattering that this is his first post 😳)

A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features @axelbarroso.bsky.social, Tommaso Cavallari, Victor Adrian Prisacariu, @ericbrachmann.bsky.social arxiv.org/abs/2510.00978

⏩ FastForward ⏩ A new model for efficient visual relocalization. Accurate camera poses without building structured 3D maps. nianticspatial.github.io/fastforward/ Work by @axelbarroso.bsky.social, Tommaso Cavallari and Victor Adrian Prisacariu.

Small but important quality of life update by @rerun.io: Customizable frustum colors. Finally we can distinguish estimates and ground truth in the same 3D view ;)

Here we go again 😅 This time I’m planning to take a more senior role to help mentor the next gen of publicity chairs. Please consider volunteering!

Recovering 6D Object Pose - Looking forward to the R6D workshop at #ICCV2025 in Hawaii! (not looking forward to the jet lag) cmp.felk.cvut.cz/sixd/worksho... The accompanying challenge is still open for submissions until Oct 1st. And the workshop also still accepts non-proceeding paper submission!

This is 100% true, including the H100 being 12.3 km away.

Did you know in Germany, there are signs in every city indicating the way to the closest H100, in case of an upcoming deadline?

I think this is a good point regarding the NeurIPS acceptance bar discussion. They turned rebuttal into endless discussions where most borderline reviewers just gave up at some point and voted accept.

I only know the R side, AND I had a reduced load but still (!), I also felt that NeurIPS put way too much load on people. It's valuable to see it playing out for once. I realized that more, more and more guidance will not fix the reviewing crisis. Instead, streamlining the process might help.

Turns out: Even reviewing mere 2 papers can be very bad, if it's NeurIPS. On top of the "normal" process, there are pages and pages of checklists, guidance and unbounded rebuttal discussions. It's ridiculous. Note to self: Never volunteer to review for them again.

Sorry folks, #ICCV2025 booked out for vegetarians.

We care about correct capitalization in the ref section, right? So it's worth me going over 100+ references to fix it, right? Like, ref capitalization is surely the first thing you check when you read a paper, and if you see "rgb-d" you are like "Pah. Not even going read this sloppy work." Right?

"This is not a simple or naive loss function; it's a well-considered piece of engineering for training a high-performance geometric deep learning model." Oh my, Gemini. Thank you 😳

Do you like developing new AI vision methods for microscopy image analysis? You love theory & implementation? 1 week left to apply for a fully funded PhD position in our lab in Dresden 🇩🇪! Topics: object detection/tracking, multimodal models & more. DM/email for details! #PhD #AcademicJobs #GPUsgoBrr

Looking forward to my talk at heidelberg.ai. I will touch on topics like #MapFreeReloc and #ACEZero, i.e. how to derive scene representations from very few (one!) or very many images.

Understanding and reconstructing the 3D world are at the heart of computer vision and graphics. At #CVPR2025, we’ve seen many exciting works in 3D vision. If you're pushing the boundaries, please consider submitting your work to #3DV2026 in Vancouver! (Deadline: Aug. 18, 2025)

Maybe it's me getting mentally inflexible, but I do not like the NeurIPS reviewer form. Too many pseudo-objective numerical rating choices of vague concepts like "Quality". And no "Justification of rating". Is that not kind of important?

I was not aware that the #ECCV2024 oral recordings are publicly available... So here is the #ACEZero talk: eccv.ecva.net/virtual/2024...

Attending @cvprconference.bsky.social and looking for a PhD or postdoc position in the area of 3d reconstruction (Gaussian splatting, nerfs, scene understanding, etc.)? Find me or drop me an email ;)

The BOP Challenge is usually the one giving out awards. Great to see it receiving one this time around 🏆 #CVPR2025

More exciting news from @nianticspatial.bsky.social today. We've announced a partnership with Snap Inc. to build a next generation #AI map that will serve as the foundation for #AR glasses and AI agents to understand, navigate and interact with the real world.

#ICCV2025 Area Chairs reminder: Rate your reviewers, including those on papers that were withdrawn.

Hoping for "The Room" level of drama.

True scientists (those embracing critical rationalism) can never be fully confident.

The #CVPR2025 main conference open access proceedings is up: openaccess.thecvf.com/CVPR2025 Workshop papers will be posted shortly. Stay tuned...

It's official: First day of Niantic Spatial, and a new focus to invent the next generation of maps. Let's do some research! www.nianticspatial.com/blog/niantic...

📢 3DV 2026 – Call for Papers is Out! 📝 Paper Deadline: Aug 18 🎥 Supplementary: Aug 21 🔗 3dvconf.github.io/2026/call-fo... 📅 Conference Date: Mar 20–23, 2026 🌆 Location: Vancouver 🇨🇦 🚀 Showcase your latest research to the world! #3DV2026 #CallForPapers #Vancouver #Canada

For two hours I have been trying to come up with a witty joke about how even the feta cheese (sic!) here is advertising with AI (sic! - recipe creator)... But I am speechless.

You now you have become senior when you stop being the person who politely ignores the random ideas thrown at you to do your actual work, and start being the person who throws random ideas at people.