Angela Dai
@adai.bsky.social
Associate Professor, 3DAI Lab @ TU Munich
https://www.3dunderstanding.org/
https://www.3dunderstanding.org/
📢ProcGen3D: 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...
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...
November 11, 2025 at 3:38 PM
📢ProcGen3D: 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...
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...
📢New in ScanNet++: High-Res 360° 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...
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...
October 30, 2025 at 4:09 PM
📢New in ScanNet++: High-Res 360° 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...
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...
📢 📢 📢 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! ⬇️
scannetpp.mlsg.cit.tum.de/scannetpp/be...
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! ⬇️
scannetpp.mlsg.cit.tum.de/scannetpp/be...
October 13, 2025 at 4:19 PM
📢 📢 📢 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! ⬇️
scannetpp.mlsg.cit.tum.de/scannetpp/be...
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! ⬇️
scannetpp.mlsg.cit.tum.de/scannetpp/be...
📢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
w/ Lukas Höllein and @niessner.bsky.social
Yueh-Cheng Liu learns 2DGS initialization, densification, and optimization priors from ScanNet++ => fast & accurate reconstruction!
Project: liu115.github.io/quicksplat
w/ Lukas Höllein and @niessner.bsky.social
May 12, 2025 at 12:17 PM
📢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
w/ Lukas Höllein and @niessner.bsky.social
Yueh-Cheng Liu learns 2DGS initialization, densification, and optimization priors from ScanNet++ => fast & accurate reconstruction!
Project: liu115.github.io/quicksplat
w/ Lukas Höllein and @niessner.bsky.social
🚀Join the 𝐒𝐜𝐚𝐧𝐍𝐞𝐭++ 𝐂𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞 @ CVPR 2025!
Think your method can handle large-scale 3D scenes?
Put it to the test:
kaldir.vc.in.tum.de/scannetpp/cv...
Updates:
✅ Preprocessed, undistorted DSLR images
✅ 3DGS demo: github.com/scannetpp/3D...
by Yueh-Cheng Liu, @cyeshwanth.bsky.social
Think your method can handle large-scale 3D scenes?
Put it to the test:
kaldir.vc.in.tum.de/scannetpp/cv...
Updates:
✅ Preprocessed, undistorted DSLR images
✅ 3DGS demo: github.com/scannetpp/3D...
by Yueh-Cheng Liu, @cyeshwanth.bsky.social
May 1, 2025 at 12:16 PM
🚀Join the 𝐒𝐜𝐚𝐧𝐍𝐞𝐭++ 𝐂𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞 @ CVPR 2025!
Think your method can handle large-scale 3D scenes?
Put it to the test:
kaldir.vc.in.tum.de/scannetpp/cv...
Updates:
✅ Preprocessed, undistorted DSLR images
✅ 3DGS demo: github.com/scannetpp/3D...
by Yueh-Cheng Liu, @cyeshwanth.bsky.social
Think your method can handle large-scale 3D scenes?
Put it to the test:
kaldir.vc.in.tum.de/scannetpp/cv...
Updates:
✅ Preprocessed, undistorted DSLR images
✅ 3DGS demo: github.com/scannetpp/3D...
by Yueh-Cheng Liu, @cyeshwanth.bsky.social
📢ScanEdit: 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
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
April 22, 2025 at 9:17 AM
📢ScanEdit: 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
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
📢ExCap3D: 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
@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
March 24, 2025 at 2:44 PM
📢ExCap3D: 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
@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