5 papers accepted at arXiv ☺️

🚀Call for #CVPR2025 workshop papers 📝 Present your latest work on Open-World 3D Scene Understanding with Foundation Models🌍☀️#CVPR2025 📆Paper Deadline: March 25 (4 pages abstract, or 8 pages paper) 🔗OpenReview: openreview.net/group?id=thecv… 🏡Details: opensun3d.github.io

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!

📢Animating the Uncaptured 📢 We animate 3D humanoid meshes using video diffusion priors given a text prompt. 🎥youtu.be/_YL1J_V3smI 🌍marcb.pro/atu Realistic motion generation for 3D characters - without motion capture! 🚀 Great work by Marc Benedí Angela Dai

📢ExCap3D: Multilevel Captioning of Objects in 3D Scenes Chandan Yeshwanth generates consistent object and part-level descriptions of objects in 3D scenes, and introduces a new dataset with 190k captions for 34k ScanNet++ objects. Project: cy94.github.io/excap3d w/ David Rozenberszki

📢ScanEdit: Hierarchically-Guided Functional 3D Scan Editing Edit complex, real-world 3D scans with text -- Mohamed El Amine Boudjoghra combines LLM reasoning with geometric optimization to produce physically plausible, instruction-aligned scene edits Check it out: aminebdj.github.io/scanedit/

📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be

🚀Join the 𝐒𝐜𝐚𝐧𝐍𝐞𝐭++ 𝐂𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞 #CVPR2025 2025! Think your method can handle large-scale 3D scenes? Put it to the test: kaldir.vc.in.tum.de/scannetpp/cvpr… Updates: ✅ Preprocessed, undistorted DSLR images ✅ 3DGS demo: github.com/scannetpp/3DGS… by Yueh-Cheng Liu, Chandan Yeshwanth

Submit your work to the NeRSemble Benchmark for photorealistic head avatars! The best methods will be featured in our CVPR 2025 workshop and receive: 📢 a 15 minute oral presentation in the workshop 🏆 an RTX 5080 GPU sponsored by NVIDIA Website: kaldir.vc.in.tum.de/nersemble_benc… #CVPR2025

📢 QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization Yueh-Cheng Liu learns 2DGS initialization, densification, and optimization priors from ScanNet++ => fast & accurate reconstruction! Project: liu115.github.io/quicksplat

The use of AI in reviewing is a growing problem. Several of my ICCV papers have AI reviews -- one reviewer was so lazy that they left in the prompts! A common refrain that I hear is that people have difficulty writing in English and need to use AI to clean up their review.

What an amazing start to our #Eurographics2025 keynotes from Justin Solomon on optimization for geometry processing - lots of useful optimization tools, and so many more interesting challenges yet to be solved!

The time for new architectures is over? Not quite! SeNaTra, a native segmentation backbone, is waiting, let's see how it works 🧵arxiv.org/abs/2505.16993

📢📢𝐁𝐈𝐆 𝐍𝐄𝐖𝐒: 𝐒𝐮𝐩𝐞𝐫 𝐞𝐱𝐜𝐢𝐭𝐞𝐝 𝐭𝐨 𝐚𝐧𝐧𝐨𝐮𝐧𝐜𝐞 𝐒𝐩𝐀𝐈𝐭𝐢𝐚𝐥 𝐀𝐈 📢📢 We’re building Spatial Foundation Models — a new paradigm of generative AI that reasons about space and time! Really stoked about our world-class team – it’s gonna be mind-boggling!

Check out Alexey Bokhovkin's cool work on factored 3d scene synthesis - also coming up at #CVPR2025 2025!

Check out our ScanNet++ workshop #CVPR2025 June 12 in 211 from 8:50am! Exciting keynotes on sota NVS & 3D understanding from Andrea Vedaldi Visual Geometry Group (VGG), Cordelia Schmid, Gordon Wetzstein, Katja Schwarz, Qianqian Wang, and leading methods on the benchmark! kaldir.vc.in.tum.de/scannetpp/cvpr…

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

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!

Good news: Soham Parekh, a PhD student in our group, will finally have the bandwidth to focus on his academic career! We just awarded him another scholarship that allows him to work remote.

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