A new model for human mesh recovery, high-performing and w/o using any 3D scans, has been published by my excellent colleagues at @naverlabseurope.bsky.social. Excellent work!

Nice article on PansSt3R with LojzeZust in #ICCV2025 Daily! rsipvision.com/ICCV2025-Tue...

If you want to learn more about general models for 3D and semantic understanding, or just have a quick chat, come meet us this afternoon at posters #462 (HAMSt3R) and #540 (PanSt3R) :)

We’re #HiringNow a Senior Research Scientist in ML for Robotics in Grenoble, France Don't miss us at #iros2025 this week to chat about the role, research & team with Darko Drakulic & @rbregier.bsky.social on Tue 21 & Thur 23 Oct! More info on where to find them & job ad ⬇️⬇️

We round off #iccv25 with highlight paper Geo4D on Thur TLDR: Geo4D repurposes a video diffusion model to reconstruct dynamic scenes in 4D Paper: arxiv.org/abs/2504.07961 Project: geo4d.github.io @chuanxiaz.bsky.social @dlarlus.bsky.social rlus.bsky.social @oxford-vgg.bsky.social gg.bsky.social 🧵9

Tuesday is Poster Session 2 with HAMS3tR: Human-Aware Multi-view Stereo 3D Reconstruction @iccv.bsky.social TLDR: HAMSt3R extends MASt3R to handle scenes involving people. Paper: arxiv.org/abs/2508.16433 @weinzaepfelp.bsky.social @vincentleroy.bsky.social 🧵7/9

It's a marathon Sunday for @gabrielacsurka.bsky.social – co-author of PANst3R, Gabriela is also giving 2 invited wksp talks AND keynote dinner speech #WiCV 😅 CALIPOSE: 🏃https://sites.google.com/view/calipose2025/ CRoCoDL: 🏃‍♀️https://localizoo.com/workshop/ WICV: sites.google.com/view/wicv-ic... 🧵6/9

If you’ve never heard the story of how the #DUSt3R or *St3R family was born & what’s going on now - don’t miss @vincentleroy.bsky.social & his new talk at the #E2E3D workshop, also Oct 19th Workshop E2E3D (afternoon): e2e3d.github.io 🧵5/9

Aloha #iccv25 – here we come! Excited to be presenting new *St3R models PANSt3R, HAMSt3R & HOSt3R. We're also introducing ‘Geo4D' and ‘LUDVIG’ 🫢 giving invited talks and mentoring! Full @iccv.bsky.social programme below (or tinyurl.com/asbn5b5d) 🧵1/9

🔥 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.!

📽️ Check out Visual Odometry Transformer! VoT is an end-to-end model for getting accurate metric camera poses from monocular videos. vladimiryugay.github.io/vot/

RaySt3R was accepted to NeurIPS! Check out the HuggingFace demo for image to 3D in cluttered scenes huggingface.co/spaces/bartd...

Wrt to RoPE: People are applying it wrongly for multi-view, if you do it VGGT style you will mix the positions of all the images. You should do it independently (i.e. no rope between images).

MapAnything: Universal Feed-Forward Metric 3D Reconstruction Nikhil Keetha et 16 al. tl;dr: VGGT meets Pow3R. No RoPE. Metric scale. arxiv.org/abs/2509.13414 1/

MapAnything: Universal Feed-Forward Metric 3D Reconstruction @nikv9.bsky.social et al. tl;dr: flexible input & metric output version of VGGT arxiv.org/abs/2509.13414

And here is a link to the thesis itself: liu.diva-portal.org/smash/record...

Towards the Next Generation of 3D Reconstruction @parskatt.bsky.social PhD Thesis. tl;dr: would be useful in teaching image matching - nice explanations. (too) Fancy and stylish notation. Cool Ack section and cover image. liu.diva-portal.org/smash/record...

How to name your method: a comprehensive flow chart

Want more visibility for your SLAM-related paper at #ICCV2025? Submit to the Nectar Track of our Neural SLAM workshop before Sep. 15! We welcome any recently published high-quality papers (ICCV, CVPR, NeurIPS, Arxiv, etc.)! 🌐 More info: sites.google.com/view/neuslam...

Adding the fab view of Grenoble by night!

The 4th day of the #PAISS2025 summer school is opened by Jérôme Revaud presenting 'Data-driven 3d vision' and the DUSt3R and MASt3R family of models.

We couldn't get more lucky with the weather last night for the #PAISS2025 gala - sponsored by @naverlabseurope.bsky.social

Third day of #PAISS2025 starts strong with a talk from @science4all.org about 'AI Security'

1/4 🚀 We’re excited to release MVTracker (ICCV 2025 Oral), the first data-driven multi-view 3D point tracker. MVTracker tracks arbitrary 3D points across multiple cameras, handling occlusions and varied camera setups without per-sequence optimization.

HOSt3R (Keypoint-free Hand-Object 3D Reconstruction from RGB images) builds upon DUSt3R for unconstrained hand-object 3D reconstruction - example 3D shape output below. Paper: arxiv.org/abs/2508.16465 More info on @naverlabseurope.bsky.social @iccv.bsky.social ➡️ tinyurl.com/2p9kcb86 2/2🧵

Announcing 2 new members of the *St3R family for human-centric 3D vision tasks! Meet HAMst3R & HOSt3R @iccv.bsky.social - HAMSt3R (Human-Aware Multi-view Stereo 3D Reconstruction) extends MASt3R to handle scenes involving people. Paper: arxiv.org/abs/2508.16433 1/2 🧵

Check out HAMSt3R 🐹 A human-aware multi-view 3D reconstruction method from NLE, accepted at ICCV 2025!

HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images Anilkumar Swamy, @vincentleroy.bsky.social @weinzaepfelp.bsky.social Jean-Sébastien Franco, Grégory Rogez tl;dr: DUSt3R tuned on hands-pose dataset + handcrafted 3D reconstruction system arxiv.org/abs/2508.16465

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction Sara Rojas, Matthieu Armando, Bernard Ghamen, @weinzaepfelp.bsky.social, @vincentleroy.bsky.social, Gregory Rogez arxiv.org/abs/2508.16433

All confirmed speakers: Andrew Davison - Nicolas Mansard - Cordelia Schmid - Marc Pollefeys - Michael Gienger - David Novotny - Andrea Vedaldi - Xavier Alameda-Pineda - Eric Brachmann - Fatma Güney - Aniruddha Kembhavi - Daniel Cremers - Adrien Gaidon - Dongwhan Lee

Major announcement ✨registration is OPEN✨ AI for Robotics workshop (4th edition): Spatial AI 🗓️Nov 21-22 Grenoble, France! Details: tinyurl.com/bdtk2nzs ⭐⭐ 14 confirmed speakers ⭐⭐: 🧵2/3 Poster submissions (travel grant possible): 🧵 3/3 Spread the word!

Naver Labs Europe organizes a Workshop on AI for Robotics in the French Alpes (Grenoble), the 4th edition. This year the topic is 'Spatial AI', registration is open!

I still can't believe the existence of this nerdy heavy metal song about a remote sensing satellite launched by @esa.int Everything about it is so damn perfect. We should have something like that for every single publicly funded project. www.youtube.com/watch?v=wPxO...

"On the Tradeoffs of SSMs and Transformers" by Albert Gu, an excellent read (why is he not on Bsky 😉) goombalab.github.io/blog/2025/tr... 1/2

We extended MUSt3R with semantic awareness and multi-view panoptic segmentation capabilities in PanSt3R, accepted at #ICCV2025 www.arxiv.org/abs/2506.21348

I gave two talks @cvprconference.bsky.social #cvpr2025 Slides are now available for those interested 1- Catch me if you can: Manoeuvre the Competition with Your Unique Abilities tinyurl.com/StandOut-DD2... 2- Beyond Long Video Understanding tinyurl.com/BeyondLong-D...

How to stand out in the crowd by @dimadamen.bsky.social!

Your #ICCV2025 paper got rejected? Give it another try and submit to our proceedings track! Your #ICCV2025 paper got accepted? Congrats! Give it even more visibility by joining our nectar track. More info: sites.google.com/view/neuslam...

Aaaand that reminds me I have to step up my oral presentation game... I felt like a freshman talking right after this 🥲

When were #CVPR2025 papers available on arXiv? 👇

I have created a starter pack with researchers from Naver Labs Europe @naverlabseurope.bsky.social: we are in Grenoble, France, and we do research in AI for robotics, computer vision, NLP, machine learning, HRI. go.bsky.app/JdTFu4Q

Wanna the outstanding performance of MASt3R while using a ViT-B or ViT-S encoder instead of its ViT-L one? Don't miss how we build DUNE, a single encoder for diverse 2D & 3D tasks, at this afternoon #CVPR2025 poster session (poster #376). paper: arxiv.org/abs/2503.14405 code: github.com/naver/dune

Checkout MUSt3R and Pow3R during this morning session at #CVPR2025 (posters 82 & 84) and give a try to their code. Get the Pow3R to integrate priors into your 3D reconstructions; and obtain nice SfM/SLAM reconstructions with MUSt3R by leverating a memory mechanism.

And if you opened an issue in DUSt3R like modalities=['depth','known_focal','known_relative_pose']*1000 for modality in modalities: print(f"How can I input {modality} in DUSt3R if I know it?") You might be interest in POW3R Friday morning, ExHall D Poster #84

A teaser of the latest 3D DUSt3R based models we’re presenting at ‪@cvprconference.bsky.social‬ Discover MUSt3R & Pow3R, universal encoder DUNE + research in navigation, vizloc, segmentation & human motion understanding! All our #CVPR2025 papers are here ➡️ tinyurl.com/4z79ujce

*3R posts are back! 🧵 Interested in SfM, RGB-SLAM or... both at the same time??? Come see MUSt3R @CVPR25 Friday morning, ExHall D Poster #82. Jerome and Boris will be there to present how we can adapt DUSt3R to multiple views via a memory mechanism. If you missed it earlier [...]

The Image Matching Challenge solution talks will be live in 10 minutes! Room 108 #CVPR2025 #IMC2025

1/ 📄 Paper 1: "DUNE: Distilling a UNiversal Encoder from Heterogeneous 2D and 3D Teachers" We propose DUNE: a ViT-based encoder distilled from multiple specialized 2D & 3D foundation models to unify visual tasks across 2D, 3D and human understanding.

Thanks Christian for the advertisement. github link: github.com/naver/dune

DUNE is a great universal image encoder which works for a large class of tasks and beats its teacher MASt3R on map free localization. #cvpr2025 We use it a lot already, I recommend it. (keynote @ Paris by @dlarlus.bsky.social )