🥳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 #CVPR2025 papers on articulated mesh generation, 4d shape generation with dictionary neural fields, large-scale 3d scene generation and editing, and 3d editing! Congrats to Daoyi Gao, Xinyi Zhang, Alexey Bokhovkin, Quan Meng, Ziya Erkoç for their amazing work!

Check out our extension of SceneScript to human-in-the-loop local corrections! Our method leverages infilling techniques from NLP to refine a 3D scene in a "one-click fix" workflow, enabling more accurate modeling of complex layouts. 📰arxiv.org/abs/2503.11806

Check out Chris' work on promptable SceneScript using infilling transformers!

Tomorrow in our TUM AI - Lecture Series we'll have Andrea Tagliasacchi (Andrea Tagliasacchi 🇨🇦), SFU. He'll talk about "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: 𝐑𝐞𝐚𝐥-𝐓𝐢𝐦𝐞 𝐃𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭𝐢𝐚𝐛𝐥𝐞 𝐑𝐚𝐲 𝐓𝐫𝐚𝐜𝐢𝐧𝐠". Live Stream: youtube.com/live/1u7ahb9bg… 5pm GMT+1 / 9am PST (Mon Mar 24th)

📢 IntrinsiX: High-Quality PBR Generation using Image Priors 📢 From text input, we generate renderable PBR maps! Next to editable image generation, our predictions can be distilled into room-scale scenes using SDS for large-scale PBR texture generation. We first train

This looks amazing! Great work Peter Kocsis !!

Aria Gen 2 glasses mark a significant leap in wearable technology, offering enhanced features and capabilities that cater to a broader range of applications and researcher needs. We believe researchers from industry and academia can accelerate their work in machine perception,

I’ll be in Nashville for #CVPR this week presenting 2 papers. Keen to connect with people interested in Generative AI and 3D Computer Vision. If you see me at the venue & are interested in connecting for projects, research positions or just a chat, feel free to say hi!

📢📢 We’ll be presenting MeshArt tomorrow morning (Friday 13.06) in the poster session at ExHall D Poster #42 from 10:30-12:30. Come and chat about articulated 3D mesh genereation or any 3D generative stuff! Project page: daoyig.github.io/Mesh_Art/

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!

Happy to report that AllTracker was accepted to #ICCV2025! The twists and turns and methodical experimentation here took at least 12 months in all. Super hard project, though in retrospect our solution is pretty simple. code: github.com/aharley/alltra… paper: arxiv.org/abs/2506.07310

Looking for a visual computing researcher to join our team working on editing of human-centric videos with diffusion models. We are training a DiT for v2v lipsync+controls, as well as seamless operations on video (frame addition/removal). Remote from Europe. DM or comment :)

Congratulations Wojciech Zielonka! 🥳🥳

Check out our #ICCV2025 paper VertexRegen! Instead of the typical incomplete meshes you get with autoreg mesh gen, VertexRegen generates progressively more detailed meshes as the generated sequence gets longer. vertexregen.github.io Great work by xzhang.dev

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art

Checkout MapAnything! A metric VGGT like model that can take additional inputs like calibration, poses or depth!

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a

Join us at the 4th Project Aria tutorial on Monday, October 20th at #ICCV2025! I'll also be giving a talk there on the stuff I've been working on recently :)

Join the Project Aria Team TODAY at "Egocentric Body Motion Tracking, Synthesis and Action Recognition" #ICCV2025 in Ballroom C on level 4. 📅 Monday, October 20 ⏰1pm-5pm in Ballroom C on Level 4 🔗egomotion-workshop.github.io Project Aria @Meta's own Lingni Ma will present a