Come check it out and chat with us at poster 160 in the morning.

We have PhD+PostDoc openings in my lab at TU Munich! Please apply by Dec 20. Come work on 3D/4D reconstruction & generation, semantic understanding and more - at the intersection of graphics, vision, and machine learning. 3dunderstanding.org/openings.html

(1/2) Check out 𝐌𝐞𝐬𝐡𝐆𝐏𝐓! MeshGPT generates triangle meshes by autoregressively sampling from a transformer model that produces tokens from a learned geometric vocabulary. As a result, we obtain clean and compact meshes :) nihalsid.github.io/mesh-gpt/ youtu.be/UV90O1_69_o

Can we synthesize 3D human-scene interactions without learning from any 3D data? Yes! Check out Lei Li's GenZI, a novel zero-shot approach to generating 3D interactions by distilling priors from large vision-language models. craigleili.github.io/projects/genzi/ youtu.be/ozfs6E0JIMY

Check out Daoyi Gao's DiffCAD - introducing probabilistic CAD retrieval and alignment to an RGB image. We captures ambiguities in depth/scale, inexact CAD matches, and don't require any training on real data! daoyig.github.io/DiffCAD/ youtu.be/PCursyPosMY

(1/2) Check out 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐀𝐯𝐚𝐭𝐚𝐫𝐬: Photorealistic Head Avatars with Rigged 3D Gaussians! We create photorealistic head avatars by animating 3D Gaussians on a parametric face model - edited and rendered in *real-time*! youtu.be/lVEY78RwU_I shenhanqian.github.io/gaussian-avata…

(1/2) LightIt: Illumination Modeling and Control for Diffusion Models! #CVPR2024 We facilitate lighting control for novel image generation from text prompts. We can also edit lighting for a given input image. Video: youtu.be/cCfSBD5aPLI Project: peter-kocsis.github.io/LightIt/

Excited to present GenZI at #CVPR2024! Lei Li introduces GenZI, the first zero-shot approach to creating realistic 3D human-scene interactions by leveraging interaction priors from large VLMs. Code and data on our website! craigleili.github.io/projects/genzi/ youtu.be/ozfs6E0JIMY

CAD retrieval with Diffusion!

How can we generate high-fidelity, complex 3D scenes? Quan Meng's LT3SD decomposes 3D scenes into latent tree representations, with diffusion on the latent trees enabling seamless infinite 3D scene synthesis! w/ Lei Li, Matthias Niessner quan-meng.github.io/projects/lt3sd/

Better optimizer for 3DGS!

Super happy to present our #NeurIPS paper 𝐂𝐨𝐡𝐞𝐫𝐞𝐧𝐭 𝟑𝐃 𝐒𝐜𝐞𝐧𝐞 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧 𝐅𝐫𝐨𝐦 𝐚 𝐒𝐢𝐧𝐠𝐥𝐞 𝐑𝐆𝐁 𝐈𝐦𝐚𝐠𝐞 in Vancouver. Come to our poster #2804 on Wednesday 11am - 2pm in East Exhibit Hall A-C and say hi if you want to learn more about 3D Scene

📢MeshArt: Generating Articulated Meshes with Structure-guided Transformers Daoyi Gao generates articulated meshes with a hierarchical transformer, modeling articulation-aware structures that guide mesh synthesis. w/ Yawar Siddiqui Lei Li Project: daoyig.github.io/Mesh_Art/

📢 ScanNet++ v2 Benchmark Release! 🏆 Test your state-of-the-art models on: 🔹 Novel View Synthesis 📸➡️🖼️ 🔹 3D Semantic & Instance Segmentation 🤖🔍🕶️ Shoutout to Chandan Yeshwanth and Yueh-Cheng Liu for their incredible work👏 🚀Check it out: kaldir.vc.in.tum.de/scannetpp/

Submit your NVS sota method to the challenge!

📢Code Release of Pixel3DMM 📢 Looking for a robust and accurate face tracker? Our state-of-the-art tracker handles challenging in-the-wild settings, such as extreme lighting conditions, fast movements, and occlusions. 👨‍💻github.com/SimonGiebenhai… 🌍simongiebenhain.github.io/pixel3dmm/

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

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…

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!

We will present QuickSplat at #ICCV2025! 🎉 Data-driven 2DGS initialization and densification makes 3D surface reconstruction fast & accurate! 🚀 Projcet: liu115.github.io/quicksplat Arxiv: arxiv.org/abs/2505.05591