🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

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)

Imagine if robots could fill in the blanks in cluttered scenes. ✨ Enter RaySt3R: a single masked RGB-D image in, complete 3D out. It infers depth, object masks, and confidence for novel views, and merges the predictions into a single point cloud. rayst3r.github.io

#CVPR2025 starts in two days, and can’t wait to share our new work! 🎉 We present ZeroGrasp, a unified framework for 3D reconstruction and grasp prediction that generalizes to unseen objects. Paper📄: arxiv.org/abs/2504.10857 Webpage🌐:sh8.io/#/zerograsp (1/4 🧵)

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

Introducing UFM, a simple end-to-end transformer for flow & covisibility, unifying optical flow & image matching! ❄️ SOTA in-the-wild Dense Correspondence ❄️ 3x Accurate & 5x Faster than RoMA ❄️ 13% Better SOTA Optical Flow ❄️ Better & 60x Faster than MASt3R Links & Insights👇

Nice work! Flow and covisibility with 'just' DiNO+self-attention. Also really appreciate the detailed analysis in the paper and supplemental.

We’ll be presenting Pow3R on Friday the 13th, from 10:30 to 12:30, during Poster Session 1 (No. 84). Would love to see you there! I’ll also be at #CVPR2025 until Sunday — happy to grab a coffee if you’re around!

*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 (and maybe do parkour?!)

In "hearing the slide" (led by Yuemin Mao ) we estimate loss of contact with a contact microphone, and use it to learn dynamic constraints. It allows moving multiple intricate objects efficiently, even objects that would otherwise be hard to grasp. fast-non-prehensile.github.io

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

Jerome Revaud Christian Wolf (🦋🦋🦋) DUSt3R has come a long way since its release & is the foundation of hundreds of '3R' papers & new 3D vision models. This vid shows some of the models by the wonderful NAVER LABS Europe team (DUSt3R, MASt3R, MASt3R-sfm, MUSt3R) & there are more 🫢! ➡️europe.naverlabs.com/research/3d-fo…

Impressive results Sungjae Park Homanga Bharadhwaj!

Excited to share our latest work in the *St3R family. PanSt3R, accepted at #ICCV25, proposes a unified and integrated approach for 3D scene reconstruction and its panoptic segmentation in a single forward pass. arxiv.org/abs/2506.21348

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the

Recent update of🚀awesome-dust3r: github.com/ruili3/awesome…🚀 - A new trend of 3D geometric reasoning: LaRI (ruili3.github.io/lari), RaySt3R (rayst3r.github.io), Amodal3R (sm0kywu.github.io/Amodal3R/). - A new direction for DUSt3R4Science: CryoFastAR (arxiv: 2506.05864).

Excited to share recent work with Kaihua Chen and Deva Ramanan where we learn to do novel view synthesis for dynamic scenes in a self-supervised manner, only from 2D videos! webpage: cog-nvs.github.io arxiv: arxiv.org/abs/2507.12646 code (soon): github.com/Kaihua-Chen/co…