We present SHAP-EDITOR, which tries to learn a universal feedforward editing function that can be applied to different objects within one second 🚀!! The demo is Hugging Face !! abs: arxiv.org/abs/2312.09246 project page: silent-chen.github.io/Shap-Editor demo: huggingface.co/spaces/silentc…

Releasing Flex3D, a two-stage pipeline for generating high-quality 3D assets in a feed-forward manner, as a further step toward high-quality 3D generation and reconstruction. Project page: junlinhan.github.io/projects/flex3…

VGG papers at ECCV 2024 – Day 2 (Wednesday) 🚀 Come to talk to our members at the poster session🥳!

Excited to share my paper "DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing" on fast 3D editing at Milan for #ECCV2024 Come to talk and chat with me at Poster # 287 on Friday morning! Project page: silent-chen.github.io/DGE/ Codes: github.com/silent-chen/DGE

🥳Excited to share my recent work at Meta, "PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models", which aims at compositional/part-level 3D generation and reconstruction from various modalities. Project page: silent-chen.github.io/PartGen/

Check out our new 3D reconstruction work, VGGT! 🥳🥳🥳 VGGT predicts all key 3D attributes (cameras, point maps, depths, point tracks) from arbitrary input views in seconds!

Check out this amazing project from Stan! The results looks super impressive!

This is amazing! We did it!

Thrilled and honored to receive the Best Paper Award at #CVPR2025! Huge thanks to my fantastic collaborators Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht, and David Novotny. Could not be there without you!