Dr. Vincent Leroy from Naver Labs Europe presenting CroCo, Dust3r, Mast3r and how large foundational models could solve 3D tasks at Map-free Visual Relocalization workshop at #ECCV2024 .

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…

arxiv.org/abs/2409.19152

MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion Paper: arxiv.org/abs/2409.19152 Code: github.com/naver/mast3r/t…

Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction monst3r-project.github.io

Not 3D vision but interesting work by Gabriela and colleagues about explainability in CV

And colloquium is starting with Vincent Leroy arguing we need one model to rule them all in 3D

🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing unposed data via feed-forward 3D reconstruction. 👉It leverages large-scale 3D datasets with minimal annotations, defining a 3D latent space. We are

MASt3R-SLAM: it's easily the most robust dense monocular SLAM system I've ever seen, and also very accurate. Real-time, RGB only (no IMU), handles unknown focal length and zoom. More new videos coming soon Eric Dexheimer Riku Murai. Paper and full info: edexheim.github.io/mast3r-slam

MUSt3R: Multi-view Network for Stereo 3D Reconstruction Yohann Cabon, Lucas Stoffl, Leonid Antsfeld, Gabriela Csurka, Boris Chidlovskii, Jerome Revaud, Vincent Leroy tl;dr: make DUSt3R symmetric and iterative+multi-layer memory mechanism->multi-view DUSt3R arxiv.org/abs/2503.01661

Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors Wonbong Jang / Won, Weinzaepfel Philippe, Vincent Leroy, Lourdes Agapito, Jerome Revaud tl;dr: DUSt3R with any optional input subset of camera intrinsics, pose and depthmaps arxiv.org/abs/2503.17316

Happy to introduce our new CVPR paper—Pow3R: Empowering Unconstrained 3D Reconstruction with Scene and Camera Priors : arxiv.org/pdf/2503.17316 Inspired by the amazing DUSt3R, which reconstructs 3D from just two unposed images, we explored: (1/n)

MAST3R-based solution won IMC-2025! kaggle.com/competitions/i… Jerome Revaud Vincent Leroy

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

RT is a bit late but well

Online reconstruction of ~400 sq meters in feed-forward regression only

Not a paper, but certainly more important than a paper… at least to me