@adai.bsky.social
Associate Professor, 3DAI Lab @ TU Munich https://www.3dunderstanding.org/
๐ข Excited to share our latest #ICCV2025 work DiffuMatch: learning spectral diffusion priors for robust non-rigid shape matching! (1/n)
16.10.2025 15:49 โ ๐ 5 ๐ 1 ๐ฌ 1 ๐ 1
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!
๐ข ๐ข ๐ข We've released the ScanNet++ Novel View Synthesis Benchmark for iPhone data!
Test your models on RGBD video featuring real-world challenges like exposure changes & motion blur!
Download the newest iPhone NVS test split and submit your results! โฌ๏ธ
scannetpp.mlsg.cit.tum.de/scannetpp/be...
๐We have PhD openings in my lab at TU Munich!
Explore 3D/4D reconstruction & generation, semantic & functional understanding, and more - at the intersection of graphics, vision, and machine learning.
๐ผPhDs are 100% E13 positions
๐Apply: 3dunderstanding.org/openings.html or via ELLIS!
Excited to join @uvadatascience.bsky.social as an Assistant Professor!
Deeply grateful to my advisors @adai.bsky.social, Maks Ovsjanikov, Hongbo Fu, and Chiew-Lan Tai for their unwavering support.
๐ฃWe are recruiting PhD students and postdocs to work on #SpatialAI. Flyer below with details!
Super excited to have @phillipisola.bsky.social give a guest lecture in our Introduction to Deep Learning course at TU Munich on representations learned by neural networks!
14.07.2025 12:27 โ ๐ 18 ๐ 0 ๐ฌ 0 ๐ 0
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 to Amine, Yueh-Cheng, @cyeshwanth.bsky.social, Haoxuan, Shivangi, and Emery for their amazing work!
Check out Xinyiโs super cool work on 4D generative modeling with dictionary neural fields - also at poster 12 in poster session 6 today! #cvpr2025
15.06.2025 18:52 โ ๐ 6 ๐ 0 ๐ฌ 0 ๐ 0
Fascinating lessons on 3D reconstruction from Andrea Vedaldi @oxford-vgg.bsky.social at the ScanNet++ workshop @cvprconference.bsky.social!
12.06.2025 16:41 โ ๐ 14 ๐ 2 ๐ฌ 0 ๐ 0
Learning about world models with Gordon Wetzstein at the ScanNet++ workshop @cvprconference.bsky.social!
12.06.2025 16:09 โ ๐ 5 ๐ 0 ๐ฌ 0 ๐ 0
Super cool insights on 4D reconstruction from Qianqian Wang at the ScanNet++ workshop @cvprconference.bsky.social!
12.06.2025 15:34 โ ๐ 7 ๐ 1 ๐ฌ 0 ๐ 0
How to generate 3D with LLM reasoning by Cordelia Schmid at the ScanNet++ workshop @cvprconference.bsky.social!
12.06.2025 14:36 โ ๐ 2 ๐ 1 ๐ฌ 0 ๐ 0
Kicking off the ScanNet++ workshop @cvprconference.bsky.social with Katja Schwarz on how to generate 3D with diffusion models!
12.06.2025 14:13 โ ๐ 7 ๐ 2 ๐ฌ 0 ๐ 0
Check out the ScanNet++ workshop @CVPR on June 12 in 211 from 8:50am!
Exciting keynotes on state-of-the-art NVS & 3D understanding from Andrea Vedaldi, Cordelia Schmid, Gordon Wetzstein, Katja Schwarz, Qianqian Wang, and leading methods on the benchmark!
kaldir.vc.in.tum.de/scannetpp/cv...
๐๐๐Announcing our $13M funding round to build the next generation of AI: ๐๐ฉ๐๐ญ๐ข๐๐ฅ ๐
๐จ๐ฎ๐ง๐๐๐ญ๐ข๐จ๐ง ๐๐จ๐๐๐ฅ๐ฌ that can generate entire 3D environments anchored in space & time. ๐๐๐
Interested? Join our world-class team:
๐ spaitial.ai
youtu.be/FiGX82RUz8U
One of Europeโs top AI researchers raised a $13M seed to crack the โholy grailโ of models
27.05.2025 07:03 โ ๐ 26 ๐ 4 ๐ฌ 3 ๐ 2
Brilliant insights from @michael-j-black.bsky.social on the importance of data and 3D+ for 4D foundation models that understand humans, and the future of embodied intelligence in the last keynote talk of #Eurographics2025!
See you next year in Aachen :)
Awesome look into the future of humanoid robots and what we can learn from character animation from Karen Liuโs keynote at #Eurographics2025!
15.05.2025 16:34 โ ๐ 7 ๐ 1 ๐ฌ 0 ๐ 0
Amazing keynote by Alyosha Efros on the role of data in visual computing at #Eurographics2025!
Thought-provoking insights from generative models to 3D perception :)
What an amazing start to our #Eurographics2025 keynotes from @justinmsolomon.bsky.social on optimization for geometry processing - lots of useful optimization tools, and so many more interesting challenges yet to be solved!
13.05.2025 14:17 โ ๐ 26 ๐ 4 ๐ฌ 0 ๐ 0๐ข๐๐ฎ๐ข๐๐ค๐๐ฉ๐ฅ๐๐ญ: 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
w/ Lukas Hรถllein and @niessner.bsky.social
๐Join the ๐๐๐๐ง๐๐๐ญ++ ๐๐ก๐๐ฅ๐ฅ๐๐ง๐ ๐ @ CVPR 2025!
Think your method can handle large-scale 3D scenes?
Put it to the test:
kaldir.vc.in.tum.de/scannetpp/cv...
Updates:
โ
Preprocessed, undistorted DSLR images
โ
3DGS demo: github.com/scannetpp/3D...
by Yueh-Cheng Liu, @cyeshwanth.bsky.social
๐ข๐๐ฎ๐ซ๐จ๐ ๐ซ๐๐ฉ๐ก๐ข๐๐ฌ ๐๐๐๐ is almost around the corner - immerse yourself in computer graphics innovation in London, May 12-16!
Register now: eg25.cs.ucl.ac.uk/main/registr...
See you in London! ๐
๐ขScanEdit: Hierarchically-Guided Functional 3D Scan Editing
Edit complex, real-world 3D scans with text -- Amine Boudjoghra combines LLM reasoning with geometric optimization to produce physically plausible, instruction-aligned scene edits
Check it out: aminebdj.github.io/scanedit/
w/ Ivan Laptev
๐ขExCap3D: Multilevel Captioning of Objects in 3D Scenes
@cyeshwanth.bsky.social 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
Tomorrow in our TUM AI - Lecture Series we'll have Andrea Tagliasacchi (@taiyasaki.bsky.social), SFU.
He'll talk about "๐๐๐๐ข๐๐ง๐ญ ๐
๐จ๐๐ฆ: ๐๐๐๐ฅ-๐๐ข๐ฆ๐ ๐๐ข๐๐๐๐ซ๐๐ง๐ญ๐ข๐๐๐ฅ๐ ๐๐๐ฒ ๐๐ซ๐๐๐ข๐ง๐ ".
Live Stream: youtube.com/live/1u7ahb9...
5pm GMT+1 / 9am PST (Mon Mar 24th)
๐ขAnimating the Uncaptured ๐ข
We animate 3D humanoid meshes using video diffusion priors given a text prompt.
๐ฅhttps://youtu.be/_YL1J_V3smI
๐https://marcb.pro/atu
Realistic motion generation for 3D characters - without motion capture! ๐
Great work by Marc Benedรญ, @adai.bsky.social
๐ขMeshPad: Interactive Sketch-Conditioned Artist-Designed Mesh Generation and Editing๐ข
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.
Tomorrow in our TUM AI - Lecture Series we'll have none other than Saining Xie (@saining.bsky.social), NYU
He'll talk about "๐๐ก๐ ๐ฆ๐ฎ๐ฅ๐ญ๐ข๐ฆ๐จ๐๐๐ฅ ๐๐ฎ๐ญ๐ฎ๐ซ๐: Why visual representation still matters".
Live stream: www.youtube.com/live/hnu-mRL...
5pm GMT+1 / 9am PST (Mon Mar 17th)
๐ The #Eurographics2025 full papers program is now online! ๐
Get ready for an exciting lineup of cutting-edge research in computer graphics!
๐ Check it out, and register now to join us in London, May 12-16!
eg25.cs.ucl.ac.uk/main/talks.h...
