Antoine Guédon

@antoine_guedon

🇫🇷Tenured researcher in AI and computer vision at @ImagineEnpc Just finished my postdoc at LIX and visit at UC Berkeley. Interests: ML, 3D, flow matching

Paris

anttwo.github.io

Replies Reposts Media

Pinned
Antoine Guédon
@antoine_guedon
Jun 15
What if you could turn any number of photos (3, 8, 15, or even 60) into one clean 3D surface (pts & mesh) with Flow Matching? Check out our new work, Surflo: Consistent 3D Surface Flow Model with Global State. 🧵 1/n 🔗anttwo.github.io/surflo/
00:00
9
Antoine Guédon
@antoine_guedon
Sep 24
🎉Surflo is a NeurIPS 2026 Oral! Huge thanks to my coauthors @nico_dufour @ShuNakamuraW @JiahuiLei1998 @kyoto_vision @akanazawa, and to the reviewers and AC. Code, model and data are released. Check it out if you're into feed-forward 3D and flow matching! anttwo.github.io/surflo/
Antoine Guédon
@antoine_guedon
Jun 15
What if you could turn any number of photos (3, 8, 15, or even 60) into one clean 3D surface (pts & mesh) with Flow Matching? Check out our new work, Surflo: Consistent 3D Surface Flow Model with Global State. 🧵 1/n 🔗anttwo.github.io/surflo/
00:00
6
Antoine Guédon
@antoine_guedon
Sep 10
I'm currently at ECCV 2026 to present Gaussian Wrapping! If you're interested in reconstructing 3D meshes from images, come see me now at Poster session 1, poster 310!
Antoine Guédon
@antoine_guedon
Aug 26
We've just released code+model for Surflo!🚀 Turn any number of photos into a 3D surface with Flow Matching. Our latent representation encodes the full scene and can be queried for downstream applications like 3D segmentation. 🔗anttwo.github.io/surflo/ 💻github.com/Anttwo/Surflo
Antoine Guédon
@antoine_guedon
Jun 15
00:29
What if you could turn any number of photos (3, 8, 15, or even 60) into one clean 3D surface (pts & mesh) with Flow Matching? Check out our new work, Surflo: Consistent 3D Surface Flow Model with Global State. 🧵 1/n 🔗anttwo.github.io/surflo/
1
Antoine Guédon
@antoine_guedon
Apr 9
🔴FROM BLOBS TO SPOKES🚲 We released paper and code for GaussianWrapping, our latest work on RGB-to-mesh! We introduce explicit geometric field formulas for Gaussians (occupancy&normals), allowing for fast and sharp surface reco (see bicycle spokes). So happy about this work!🤩
Diego Gomez
@DiegoGomezLIX
Apr 9
1/n 🧵 Introducing Gaussian Wrapping — a principled framework for extracting high-quality meshes from 3DGS! 🚲 We recover thin structures, like bicycle spokes, where all prior methods fail. Follow the thread for a brief overview and links!
00:00