Angela Dai
@adai.bsky.social
๐ค 2257
๐ฅ 104
๐ 35
Associate Professor, 3DAI Lab @ TU Munich
https://www.3dunderstanding.org/
reposted by
Angela Dai
CVMP
28 days ago
The first keynote today at
#CVMP2025
is by Angela Dai
@adai.bsky.social
from 3DAI Lab at TU Munich "Can Transformers speak geometry?" There are lots of different 3D representations we use in learning but industry widely uses meshes.
1
8
3
reposted by
Angela Dai
CVMP
29 days ago
And four fantastic keynotes from Yi-Zhe Song
@peoplecentredai.bsky.social
, Christian Richardt
@cr333.bsky.social
, Angela Dai
@adai.bsky.social
, and Peter Hedman
@peterhedman.bsky.social
#CVMP2025
1
3
2
reposted by
Angela Dai
CVMP
29 days ago
And that's a start ๐คฉ We kick off the 22nd ACM SIGGRAPH European Conference on Visual Media Production at BFI Southbank in London Where industry and academia meet ๐ค๐ฌ
#CVMP2025
#BFI
#BFISouthbank
1
2
1
๐ขProcGen3D: 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/Proc...
loading . . .
about 2 months ago
0
7
1
๐ขNew in ScanNet++: High-Res 360ยฐ Panos! Chandan Yeshwanth and 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/do...
Code
github.com/scannetpp/sc...
loading . . .
2 months ago
0
5
1
reposted by
Angela Dai
3 months ago
๐ข Excited to share our latest
#ICCV2025
work DiffuMatch: learning spectral diffusion priors for robust non-rigid shape matching! (1/n)
1
7
4
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...
loading . . .
3 months ago
1
4
0
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!
3 months ago
0
9
1
reposted by
Angela Dai
Lei Li
4 months ago
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!
0
1
1
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!
6 months ago
0
18
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!
6 months ago
0
9
1
Check out Xinyiโs super cool work on 4D generative modeling with dictionary neural fields - also at poster 12 in poster session 6 today!
#cvpr2025
add a skeleton here at some point
7 months ago
0
6
0
Fascinating lessons on 3D reconstruction from Andrea Vedaldi
@oxford-vgg.bsky.social
at the ScanNet++ workshop
@cvprconference.bsky.social
!
7 months ago
0
14
2
Learning about world models with Gordon Wetzstein at the ScanNet++ workshop
@cvprconference.bsky.social
!
7 months ago
0
5
0
Super cool insights on 4D reconstruction from Qianqian Wang at the ScanNet++ workshop
@cvprconference.bsky.social
!
7 months ago
0
7
1
How to generate 3D with LLM reasoning by Cordelia Schmid at the ScanNet++ workshop
@cvprconference.bsky.social
!
7 months ago
0
2
1
Kicking off the ScanNet++ workshop
@cvprconference.bsky.social
with Katja Schwarz on how to generate 3D with diffusion models!
7 months ago
0
7
2
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...
7 months ago
0
13
6
reposted by
Angela Dai
Matthias Niessner
7 months ago
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
loading . . .
SpAItial AI: Building Spatial Foundation Models
YouTube video by SpAItial AI
https://youtu.be/FiGX82RUz8U
4
53
9
reposted by
Angela Dai
TechCrunch
7 months ago
One of Europeโs top AI researchers raised a $13M seed to crack the โholy grailโ of models
loading . . .
One of Europeโs top AI researchers raised a $13M seed to crack the โholy grailโ of models | TechCrunch
One of Europeโs most prominent AI researchers, Matthias Niessner, is now the CEO of SpAItial, a startup working on spatial foundation models.
https://techcrunch.com/2025/05/26/one-of-europes-top-ai-researchers-raised-a-13m-seed-to-crack-the-holy-grail-of-models/?utm_campaign=social&utm_source=bluesky&utm_medium=organic
3
26
6
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 :)
8 months ago
0
19
1
Awesome look into the future of humanoid robots and what we can learn from character animation from Karen Liuโs keynote at
#Eurographics2025
!
8 months ago
0
7
1
Amazing keynote by Alyosha Efros on the role of data in visual computing at
#Eurographics2025
! Thought-provoking insights from generative models to 3D perception :)
8 months ago
0
14
2
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!
8 months ago
0
26
4
๐ข๐๐ฎ๐ข๐๐ค๐๐ฉ๐ฅ๐๐ญ: 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
loading . . .
8 months ago
0
22
4
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
loading . . .
8 months ago
1
11
4
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
8 months ago
0
6
2
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
loading . . .
8 months ago
0
9
0
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
loading . . .
9 months ago
0
2
0
reposted by
Angela Dai
Matthias Niessner
9 months ago
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)
loading . . .
TUM AI Lecture Series - Radiant Foam: Real-Time Differentiable Ray Tracing (Andrea Tagliasacchi)
YouTube video by Matthias Niessner
https://youtube.com/live/1u7ahb9bgj8
0
20
3
reposted by
Angela Dai
Matthias Niessner
10 months ago
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
loading . . .
1
11
3
reposted by
Angela Dai
Matthias Niessner
10 months ago
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.
loading . . .
1
22
5
reposted by
Angela Dai
Matthias Niessner
10 months ago
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)
loading . . .
TUM AI Lecture Series - The multimodal future: Why visual representation still matters (Saining Xie)
YouTube video by Matthias Niessner
https://www.youtube.com/live/hnu-mRLebhc?si=Xr0dt6ai9QziXl7o
0
22
4
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...
10 months ago
0
8
0
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!
10 months ago
1
18
3
reposted by
Angela Dai
Chris Offner
11 months ago
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
1
45
10
reposted by
Angela Dai
Matthias Niessner
11 months ago
Tomorrow in our TUM AI - Lecture Series with none other than Robin Rombach, CEO Black Forest Labs. He'll talk about "๐ ๐๐๐: Flow Matching for Content Creation at Scale". Live stream:
youtube.com/live/nrKKLJX...
6pm GMT+1 / 9am PST (Mon Feb 17rd)
loading . . .
TUM AI Lecture Series - FLUX: Flow Matching for Content Creation at Scale (Robin Rombach)
YouTube video by Matthias Niessner
https://youtube.com/live/nrKKLJXBSw0
0
33
10
reposted by
Angela Dai
Lingjie Liu
11 months ago
๐ข Calling all PhD students in Computer Graphics! The
#Eurographics2025
Doctoral Consortium deadline is just one week away (Feb 13)! Don't miss this opportunity to present your research, receive expert feedback, and connect with fellow PhD students. ๐ Apply now:
eg25.cs.ucl.ac.uk/main/callfor...
0
4
1
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...
11 months ago
1
29
5
reposted by
Angela Dai
Silvia Sellรกn
11 months ago
Didn't quite make it to SIGGRAPH? Consider submitting to SGP, the abstract deadline is tomorrow:
sgp2025.my.canva.site/submit-page-...
0
17
5
reposted by
Angela Dai
Matthias Niessner
11 months ago
Tomorrow in our TUM AI - Lecture Series with none other than George Drettakis. He'll talk about "๐๐ก๐ ๐๐ ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐ฉ๐ฅ๐๐ญ๐ญ๐ข๐ง๐ ๐๐๐ฏ๐๐ง๐ญ๐ฎ๐ซ๐: ๐๐๐ฌ๐ญ, ๐๐ซ๐๐ฌ๐๐ง๐ญ, ๐ ๐ฎ๐ญ๐ฎ๐ซ๐". Live stream:
youtube.com/live/DjOqkVI...
5pm GMT+1 / 8am PST (Mon Feb 3rd)
loading . . .
TUM AI Lecture Series - The 3D Gaussian Splatting Adventure: Past, Present, Futur (George Drettakis)
YouTube video by Matthias Niessner
https://youtube.com/live/DjOqkVIlEGY
0
30
4
๐ข ScanNet++ v2 Benchmark Release! ๐ Test your state-of-the-art models on: ๐น Novel View Synthesis ๐ธโก๏ธ๐ผ๏ธ ๐น 3D Semantic & Instance Segmentation ๐ค๐๐ถ๏ธ Shoutout to @awhiteguitar.bsky.social & Yueh-Cheng Liu for their incredible work๐ ๐Check it out:
kaldir.vc.in.tum.de/scannetpp/
loading . . .
11 months ago
0
30
10
๐ ๐๐ฎ๐ซ๐จ๐ ๐ซ๐๐ฉ๐ก๐ข๐๐ฌ ๐๐๐๐ - Registration is Open! ๐ป๐จ 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! ๐ Register now:
eg25.cs.ucl.ac.uk/main/registr...
11 months ago
1
32
7
reposted by
Angela Dai
Justin Solomon
12 months ago
Announcing SGI 2025! Undergrads and MS students: Apply for 6 weeks of paid summer geometry processing research. No experience needed: 1 week tutorials + 5 weeks of projects. Mentors are top researchers in this emerging branch of graphics/computing/math.
sgi.mit.edu
loading . . .
3
70
41
Excited to announce ScanNet++ v2!๐
@awhiteguitar.bsky.social
& Yueh-Cheng Liu have been working tirelessly to bring: ๐น1006 high-fidelity 3D scans ๐น+ DSLR & iPhone captures ๐น+ rich semantics Elevating 3D scene understanding to the next level!๐ w/
@niessner.bsky.social
kaldir.vc.in.tum.de/scannetpp
loading . . .
about 1 year ago
1
64
15
๐ขMeshArt: 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 Page:
daoyig.github.io/Mesh_Art/
loading . . .
about 1 year ago
1
14
6
reposted by
Angela Dai
Silvia Sellรกn
about 1 year ago
SGP 2025 will take place in Bilbao between June 30th and July 4th, and I am one of the Technical Program Co-Chairs. For the first time, we are introducing an *early* paper deadline on **February 7th**!
1
30
12
reposted by
Angela Dai
Manuel Dahnert
about 1 year ago
Super happy to present our
#NeurIPS
paper ๐๐จ๐ก๐๐ซ๐๐ง๐ญ ๐๐ ๐๐๐๐ง๐ ๐๐ข๐๐๐ฎ๐ฌ๐ข๐จ๐ง ๐ ๐ซ๐จ๐ฆ ๐ ๐๐ข๐ง๐ ๐ฅ๐ ๐๐๐ ๐๐ฆ๐๐ ๐ in Vancouver. Come to our poster #2804 on Wednesday 11am - 2pm in East Exhibit Hall, if you want to learn more about 3D Scene Diffusion! See you tomorrow! Project Page:
manuel-dahnert.com/research/sce...
1
8
5
reposted by
Angela Dai
Matthias Niessner
about 1 year ago
๐ข ๐๐ซ๐๐๐ข๐ญ๐จ๐ซ๐๐: ๐ ๐๐ฌ๐ญ ๐๐ง๐ ๐๐ซ๐๐๐ข๐ฌ๐ ๐๐ ๐๐ก๐๐ฉ๐ ๐๐๐ข๐ญ๐ข๐ง๐ ๐ข We propose a training-free 3D shape editing approach that rapidly and precisely edits the regions intended by the user and keeps the rest as is.
loading . . .
1
9
4
๐ขDNF: Generating 4D animations with dictionary-based neural fields! Xinyi Zhang presents a new dictionary-based neural field for unconditional 4D generation of deforming shapes -- generating motions with high-quality shape and temporal consistency.
xzhang-t.github.io/project/DNF/
loading . . .
about 1 year ago
0
29
6
Load more
feeds!
log in