📢Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image📢 We directly regress neural parametric head models (NPHMs) from a single image — fast, stable, and significantly more expressive than classical 3DMMs such as FLAME.

📢 Intrinsic Image Fusion for Multi-View 3D Material Reconstruction 📢 We combine generative material priors with inverse path tracing: 1) define a parametric texture space 2) fuse monocular predictions across views into consistent textures

Today in our TUM AI - Lecture Series we'll have the amazing Ruiqi Gao, Google DeepMind. She'll talk about "𝐁𝐮𝐢𝐥𝐝𝐢𝐧𝐠 𝐠𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐯𝐞 𝐰𝐨𝐫𝐥𝐝 𝐦𝐨𝐝𝐞𝐥𝐬: progress and challenges". Live stream: www.youtube.com/live/CkOSMqw... 7pm GMT+1 / 10am PST (Tue Dec 16th).

📢📢 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 and style inputs from images or text.

#ICCV last week was incredible — catching up with so many people, chatting about research, and, most importantly, having lots of fun. Still hard to fathom this privilege as a researcher — getting to travel to such amazing places and be part of this brilliant community - Thanks!

The hot topic at #ICCV2025 was World Models. They come in different flavors — (interactive) video models, neural simulators, reconstruction models, etc. — but the overarching goal is clear: Generative AI that predict and simulate how the real world works.

Hawaii on the same scale as the United Kingdom.

𝐺𝑒𝑛𝑒𝑟𝑎𝑡𝑜 𝑒𝑟𝑔𝑜 𝑠𝑢𝑚 — I generate, therefore I am.

for more documentation: github.com/scannetpp/sc... Huge thanks to Yueh-Cheng Liu, as well as Chandan Yeshwanth and @niessner.bsky.social for their incredible work!

In the 'early days' of modern deep learning (2012-2015) when ConvNets such as AlexNet or VGG came out, it was considered almost impractical to train an ImageNet classifier from scratch.

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 :)

All six of our submissions were accepted to #NeurIPS2025 🎉🥳 Awesome works about Gaussian Splatting Primitives, Lighting Estimation, Texturing, and much more GenAI :) Great work by Peter Kocsis, Yujin Chen, Zhening Huang, Jiapeng Tang, Nicolas von Lützow, Jonathan Schmidt 🔥🔥🔥

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! 🌍http://mschneider456.github.io/world-explorer/ 📽️https://youtu.be/N6NJsNyiv6I

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. shivangi-aneja.github.io/projects/sca...

📢 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. 📷https://youtu.be/ecK9m3LXg2c 🌍https://litereality.github.io

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...

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.

#CVPR submissions per year have significantly increased. Now over 11k / year with an expectation to grow even further. This comes with a lot of implications, how to handle the reviews, presentations, etc. Kudos to the organizers for all the efforts that went into it.

Super excited to be in Nashville for #CVPR2025! Looking forward to catching up with everyone -- feel free to reach out if you want to chat! Everything is a Honky Tonk :)

📢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. 🌍https://lnkd.in/evNt8bV2 📷https://lnkd.in/ekB5QeEK

📢Code Release of Pixel3DMM 📢 Looking for a robust and accurate face tracker? We handle challenging in-the-wild settings, such as extreme lighting conditions, fast movements, and occlusions. 👨‍💻https://lnkd.in/e3dX23WV 🌍https://lnkd.in/eQ3Zpn3J Pixel3DMM can be run on videos and single images.

📢PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors📢 We propose a new optimization to up-sample textures of 3D assets (albedo, roughness, metallic, and normal maps) by leveraging 2D super-resolution models. 📝http://arxiv.org/abs/2506.02846 📽️https://youtu.be/eaM5S3Mt1RM

One of Europe’s top AI researchers raised a $13M seed to crack the ‘holy grail’ of models

🚀🚀🚀Announcing our $13M funding round to build the next generation of AI: 𝐒𝐩𝐚𝐭𝐢𝐚𝐥 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 that can generate entire 3D environments anchored in space & time. 🚀🚀🚀 Interested? Join our world-class team: 🌍 spaitial.ai youtu.be/FiGX82RUz8U

📢GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans📢 We reconstruct hair strands from colorless 3D scans by extracting orientation cues directly from the mesh surface geometry by finding local characteristic lines and from shaded renderings using a neural 2D line detector.

📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals & UV-coordinates estimation. These cues from our 2D foundation model constrain the 3DMM parameters, achieving great accuracy.

📢 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. 🌍 nicolasvonluetzow.github.io/LinPrim/

📢 SHeaP: Self-Supervised Head Predictor Learned via 2D Gaussians 📢 Given a single input image, we predict accurate 3D head geometry, pose, and expression. 🌍 nlml.github.io/sheap/ 🎥 youtu.be/vhXsZJWCBMA/ Great work by Liam Schoneveld, Davide Davoli, Jiapeng Tang

📢 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.

📢Announcing our 3D head avatar benchmark📢 Two tasks with hidden test sets: - Dynamic Novel View Synthesis on Heads - Monocular FLAME-driven Head Avatar Reconstruction Our goal is to make research on 3D head avatars more comparable and ultimately increase the realism of digital humans.

Tomorrow in our TUM AI - Lecture Series we'll have Andrea Tagliasacchi (@taiyasaki.bsky.social), SFU. He'll talk about "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: 𝐑𝐞𝐚𝐥-𝐓𝐢𝐦𝐞 𝐃𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭𝐢𝐚𝐛𝐥𝐞 𝐑𝐚𝐲 𝐓𝐫𝐚𝐜𝐢𝐧𝐠". Live Stream: youtube.com/live/1u7ahb9... 5pm GMT+1 / 9am PST (Mon Mar 24th)

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

📢MeshPad: Interactive Sketch-Conditioned Artist-Designed Mesh Generation and Editing📢 Users can interactively design 3D models just from a sketch-based interface - check it out! We break down the design process into addition with an autoregressive generator and deletion operations by a classifier.

📢📢Want to build 𝟑𝐃 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬? 📢📢 ➡️We're looking for Diffusion/3D/ML/Infra engineers and scientists in Munich & London. Get in touch for details! #3D #GenAI #spatialintelligence #foundationmodels

Tomorrow in our TUM AI - Lecture Series we'll have none other than Saining Xie (@saining.bsky.social), NYU He'll talk about "𝐓𝐡𝐞 𝐦𝐮𝐥𝐭𝐢𝐦𝐨𝐝𝐚𝐥 𝐟𝐮𝐭𝐮𝐫𝐞: Why visual representation still matters". Live stream: www.youtube.com/live/hnu-mRL... 5pm GMT+1 / 9am PST (Mon Mar 17th)

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, and Ziya Erkoc for their amazing work!

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. youtu.be/P3zNVx15gYs tobias-kirschstein.github.io/avat3r Great work by Tobias Kirschstein with J. Romero, A. Sevastopolsky, S. Saito.

ETH starts a series of exciting guest talks on Robotics, Vision, and Controls this week. Tomorrow at 12:00 Zurich time, @adai.bsky.social from TU Munich will give a talk titled "From Quantity to Quality for 3D Perception." robotics-talks.com #robotics

Happening now! Join us if you want to more about #diffusion #stablediffusion #flux and many more :)

Tomorrow in our TUM AI - Lecture Series with none other than Robin Rombach, CEO Black Forest Labs. He'll talk about "𝐅𝐋𝐔𝐗: Flow Matching for Content Creation at Scale". Live stream: youtube.com/live/nrKKLJX... 6pm GMT+1 / 9am PST (Mon Feb 17rd)

(1/n) 📢📢 𝐍𝐞𝐑𝐒𝐞𝐦𝐛𝐥𝐞 𝐯𝟐 𝐃𝐚𝐭𝐚𝐬𝐞𝐭 𝐑𝐞𝐥𝐞𝐚𝐬𝐞 📢📢 Head captures of 7.1MP from 16 cameras at 73fps: * More recordings (425 people) * Better color calibration * Convenient download scripts github.com/tobias-kirsc...

Excited to bring back the 2nd ScanNet++ Novel View Synthesis and 3D Semantic Understanding Challenge at #CVPR 2025! Submit to our new benchmark, now with over 1000 high-fidelity scans of real-world scenes: kaldir.vc.in.tum.de/scannetpp/ Check it out: kaldir.vc.in.tum.de/scannetpp/cv...

Happening now - join us if you like 3D Gaussian Splatting!!!

Tomorrow in our TUM AI - Lecture Series with none other than George Drettakis. He'll talk about "𝐓𝐡𝐞 𝟑𝐃 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐒𝐩𝐥𝐚𝐭𝐭𝐢𝐧𝐠 𝐀𝐝𝐯𝐞𝐧𝐭𝐮𝐫𝐞: 𝐏𝐚𝐬𝐭, 𝐏𝐫𝐞𝐬𝐞𝐧𝐭, 𝐅𝐮𝐭𝐮𝐫𝐞". Live stream: youtube.com/live/DjOqkVI... 5pm GMT+1 / 8am PST (Mon Feb 3rd)

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

🚀 𝐄𝐮𝐫𝐨𝐠𝐫𝐚𝐩𝐡𝐢𝐜𝐬 𝟐𝟎𝟐𝟓 - Registration is Open! 💻🎨 Join us in London, May 12-16, 2025, for one of the leading Computer Graphics conferences in the world and an incredible week of research innovation! 🔗 Register now: eg25.cs.ucl.ac.uk/main/registr...

With DeepSeek, opinions are shifting from "winning in AI needs infinite compute" to "all cutting-edge models are cheap and free". It's somewhat obvious that brute-force compute was a bad idea, while at the same time, training big models still takes significant resources.

Winter is coming on our TUM campus in Garching :)

Merry Christmas & Happy Holidays🎅🎄🕯️ May your tokens generate well, noise diffuse smoothly, splats shine with radiance, and your GPUs burn bright - but not out! Splat-acular holidays everyone!

Excited to announce ScanNet++ v2!🎉 @awhiteguitar.bsky.social & Yueh-Cheng Liu have been working tirelessly to bring: 🔹1006 high-fidelity 3D scans 🔹+ DSLR & iPhone captures 🔹+ rich semantics Elevating 3D scene understanding to the next level!🚀 w/ @niessner.bsky.social kaldir.vc.in.tum.de/scannetpp