Check out the EnvGS code. Now open-source! Recently added: high-quality real-time GUI rendering to view base color, reflection color, normal map, and depth map. EnvGS performs exceptionally well on highly specular indoor scene reconstruction. Link in the comments! 👇

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

Amazing in-the-wild video relighting results! I like the quality of the cast shadows, showing that current diffusion models have understanding about light propagation.

Check out our #ICCV2025 work on functional 3d scan editing, learning to optimize, multi-level 3d captioning, interactive mesh editing, audio-driven avatars, & shape matching! Congrats Mohamed El Amine Boudjoghra, Yueh-Cheng Liu, Chandan Yeshwanth, Haoxuan Li, Shivangi, Emery for amazing work!

📢 LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans🏠✨ -> converts RGB-D scans into compact, realistic, and interactive 3D scenes — featuring high-quality meshes, PBR materials, and articulated objects. 📷youtu.be/ecK9m3LXg2c 🌍litereality.github.io

ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions (#SIGGRAPH) We reconstruct ultra-high fidelity photorealistic 3D avatars capable of generating realistic and high-quality animations including freckles and other fine facial details. We operate on patch-based

📢Code release for 3DGS-LM (#ICCV2025)📢 Gaussian-Splatting made faster by changing the underlying optimizer. It's compatible with other changes that accelerate the optimization along different axes. lukashoel.github.io/3DGS-LM/

HairGS: Hair Strand Reconstruction based on 3D Gaussian Splatting (#BMVC2025) 📢 We reconstruct realistic 3D hair strands from multi-view images in ~1 hour. Results show robustness to a wide range of hair styles such as challenging curly hair. Project: yimin-pan.github.io/hair-gs/

Can we use video diffusion to generate 3D scenes? 𝐖𝐨𝐫𝐥𝐝𝐄𝐱𝐩𝐥𝐨𝐫𝐞𝐫 (#SIGGRAPHAsia25) creates fully-navigable scenes via autoregressive video generation. Text input -> 3DGS scene output & interactive rendering! 🌍mschneider456.github.io/world-explorer/ 📽️youtu.be/N6NJsNyiv6I

🎉Our paper, 𝗜𝗻𝘁𝗿𝗶𝗻𝘀𝗶𝗫, just got accepted to #NeurIPS2025! 🎉 Our model generates renderable PBR maps directly from text and can also be used for rooms-scale scene texturing using SDS. peter-kocsis.github.io/IntrinsiX/ Let's meet in San Diego!

So You Want to Be an Academic? A couple of years into your PhD, but wondering: "Am I doing this right?" Most of the advice is aimed at graduating students. But there's far less for junior folks who are still finding their academic path. My candid takes: anandbhattad.github.io/blogs/jr_grads…

Fantastic retreat this weekend by our research groups! Internal reviews, ideas brainstorming, paper reading, and much more! Of course also many social activities -- the highlight being our kayaking trip - lots of fun :)

📢 Code for 𝙄𝙣𝙩𝙧𝙞𝙣𝙨𝙞𝙓: High-Quality PBR Generation using Image Priors 📢 We have just released the inference code and the pre-trained weights! Our model generates intrinsic properties (albedo, roughnes, metallic, normal) directly from text. peter-kocsis.github.io/IntrinsiX/

📢New in ScanNet++: High-Res 360° Panos! Chandan Yeshwanth & Yueh-Cheng Liu have added pano captures for 956 ScanNet++ scenes, fully aligned with the 3D meshes, DSLR, and iPhone data - multiple panos per scene Check it out: Docs kaldir.vc.in.tum.de/scannetpp/docu… Code github.com/scannetpp/scan…

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls

📢ProcGen3D: Learning Neural Procedural Graphs for Image-to-3D Reconstruction Xinyi Zhang learns neural procedural graphs to generate high-fidelity 3D - MCTS-guided sampling maintains consistency with the input image, even from real images! Check it out: xzhang-t.github.io/project/ProcGe…

Congrats Yawar Siddiqui! Amazing work, really well-deserved!

FLUX.2 is here - our most capable image generation & editing model to date. Multi-reference. 4MP. Production-ready. Open weights. Into the new.

📢 𝙄𝙣𝙩𝙧𝙞𝙣𝙨𝙞𝙓 NeurIPS Conference If you are excited about PBR materials, drop by at Wednesday from 4:30pm to 7:30pm (poster 4308), or feel free to dm me. PS: We have just released the training code, so you can also train your own models now! peter-kocsis.github.io/IntrinsiX/

Radiance Meshes for Volumetric Reconstruction 🎉 We made a thing! A Radiance Field that is composited out of a triangle meshes that renders accurately the underlying volumetric field, with no popping AND faster than approximate methods like Gaussian Splatting.