Great work by Simon Giebenhain! Maybe the best open-source FLAME tracker out there at the moment. Additionally, the face normal and UV estimation networks are available which can be tremendously useful even in other scenarios than tracking. Check it out!

📢BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading We propose a hybrid neural shading scheme for creating intrinsically decomposed 3DGS head avatars, that allow real-time relighting and animation. 🌍jonathsch.github.io/becominglit/ 📷youtu.be/xPyeIqKdszA

Jonathan spent a whole year to build all the wiring, the programmable lights, the controllers etc for the Lightstage himself. Now we can finally see the amazing results of his hard work. Can't stop looking at the relighting of the avatars :O

I will be at #CVPR25! 🤗 Please come chat with me and Ethan Weber - during our poster session for Pippo, on Sat 5-7pm (Hall D)! 👋

BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading TLDR: A method for relighting and animating Gaussian Avatars in realtime, by learning a neural network for diffuse BRDF and an analytical specular term. This work also introduces a multiview, multi-light

Check out the ScanNet++ workshop! I’ll be there tomorrow!

Happening now in room 110A! Shunsuke Saito Shunsuke Saito talking about Codec Avatars!

Congrats to zhiwen chen and Linzhou Li for winning the NeRSemble benchmark challenges with their TaoAvatar and RGBAvatar methods! Well-deserved first places! #CVPR2025

Presenting PrEditor3D at #CVPR2025 📢📢 If you'd like to learn more about our work and discuss 3D generation/editing, come visit our poster on Friday, June 13th, in ExHall D between 10:30-12:30 (Poster #44). Project Page: ziyaerkoc.com/preditor3d

📢📢 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/

Join us tomorrow for a chat about 3D Scene Generation with Diffusion Models and more! Stop by our LT3SD poster and say hello! Drop me a DM if you’d like to meet! #CVPR2025 🗓️ Fri 13 Jun 11:30 – 13:30 📍 ExHall D Poster #45 Check more details in quan-meng.github.io/projects/lt3sd

Presenting GAF at #CVPR2025 📢📢 If you'd like to discuss Gaussian Avatar Reconstruction and Multi-view Diffusion, come visit our poster on Friday, June 13th, in ExHall D between 16:00-18:00 （Poster #10). Project Page：tangjiapeng.github.io/projects/GAF/

Attending #CVPR2025 in Nashville with our groups from TU München. Excited to be in the music city and presenting our research from last year :)

Want to work on cutting-edge #AI? We have several fully-funded 𝐏𝐡𝐃 & 𝐏𝐨𝐬𝐭𝐃𝐨𝐜 𝐨𝐩𝐞𝐧𝐢𝐧𝐠𝐬 in our Visual Computing & AI Lab in Munich! Apply here: application.vc.in.tum.de Topics have a strong focus on Generative AI, 3DGs, NeRFs, Diffusion, LLMs, etc.

3DGH: 3D Head Generation with Composable Hair and Face TLDR: A Generative model of (static) Gaussian Avatars using a GAN. Here the head and hair are modelled separately with templates, and data is generated synthetically. 📽️ Project Page: c-he.github.io/projects/3dgh/ 📜 Paper:

Seven papers accepted at #ICCV2025! Exciting topics: lots of generative AI using transformers, diffusion, 3DGS, etc. focusing on image synthesis, geometry generation, avatars, and much more - check it out! So proud of everyone involved - let's go🚀🚀🚀 niessnerlab.org/publications.h…