I will be presenting MultiHMR today as an invited poster of the 3D Humans Workshop (8:30-9:15 am ; 12:30-1:30 pm) and makes a short presenting at the Rhobin Workshop as a winner of the 3D human reconstruction task of the challenge (2:30pm). #CVPR24

Busy 1st day for us #CVPR2026 workshops - check out the full program ➡️tinyurl.com/mw3zn8e8 Lots of 3D reconstruction with DUSt3R (& MASt3R...) but also #multi-hmr, lifelong learning & vizloc ! Diane Larlus Jerome Revaud Vincent Leroy Fabien Baradel

CroCo-man presented by Weinzaepfel Philippe and Vincent Leroy! Nice poster 😊

Be sure to check out the DUSt3R poster tomorrow (Friday) morning. It's absolutely insane to me that DUSt3R isn't an highlight, oral, award candidate, or award winner. I'm willing to bet it'll win a Test of Time award a decade from now. github.com/naver/dust3r

If you are interested in navigation in real environments and in multi-task policies, come to see us at posters 313 and 314!

Training code for Multi-HMR is now available #ECCV2024

By finetuning CroCo for relative pose and visibility estimation and using that in an agent, we reach SOTA image goal. Code is now available. #ICLR2024👇

Want to distill diverse visual encoders into a universal one that outperforms all original ones? Then check out our #ECCV2024 paper! UNIC: Universal Classification Models via Multi-teacher Distillation europe.naverlabs.com/unic A quick summary 🧵 (1/6)

Want to know more about single frame #mapfree localization benchmark winner🏆 #MASt3R & all our other presentations, posters & demos at #ECCV2024 this week? Here's a summary & schedule for the week➡️europe.naverlabs.com/blog/naver-ecc…

Great #ECCV2024 oral presentation from Vincent Leroy on MAST3R NAVER LABS Europe

Second demo day, SECOND TO NONE😎😉!!! #ECCV2024 demos this morning are about event camera practical usage, building IKEA forniture FOR DUMMIES, better call SAL (I did not find a better claim-check it out!), RT multi person SMPL 😱, augmented reality + a CORGI🐶🐕

Ginger is presenting this morning how to derive a rich and versatile human pose representation by combining several modalities #ECCV2024

Diane Larlus Weinzaepfel Philippe Diane Larlus Weinzaepfel Philippe @skamalas Thomas Lucas 🎉🎊

MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion Bardienus Duisterhof Lojze Zust Weinzaepfel Philippe Vincent Leroy Yohann Cabon Jerome Revaud tl;dr: anchor points (but not quantize) for dense corrs for BA. viewgraph from retrieval arxiv.org/abs/2409.19152

When was #ECCV2024 papers available on arXiv ? 👇

📢 Job Alert 📢 NAVER LABS Europe My team is looking for a Research Scientist in Visual Representation Learning - More info tinyurl.com/3jz935fk

Announcing 2 new members of the *St3R family for human-centric 3D vision tasks! Meet HAMst3R & HOSt3R #ICCV2025 #iccv2025 - HAMSt3R (Human-Aware Multi-view Stereo 3D Reconstruction) extends MASt3R to handle scenes involving people. Paper: arxiv.org/abs/2508.16433 1/2 🧵

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 NAVER LABS Europe at #iccv2025 ➡️tinyurl.com/2p9kcb86 2/2🧵