Angela Dai

@angelaqdai • 9,735 subscribers

Associate Professor @ Technical University of Munich

Shorts

12,876 views

14,643 views

11,913 views

13,338 views

Videos

sweetdream.ai

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Private Show

Join now for exclusive access

Free preview available • Premium content

41,577 views • 20 days ago

106,862 views • 2 years ago

19,645 views • 4 months ago

17,876 views • 3 months ago

12,130 views • 2 months ago

47,567 views • 1 year ago

27,302 views • 1 year ago

29,422 views • 1 year ago

14,639 views • 8 months ago

18,842 views • 1 year ago

17,749 views • 1 year ago

12,987 views • 1 year ago

12,627 views • 1 year ago

20,508 views • 2 years ago

13,433 views • 1 year ago

15,586 views • 2 years ago

11,586 views • 2 years ago

10,286 views • 2 years ago

No more content to load

Live Cam

Angela Dai

Shorts

📢New in ScanNet++: High-Res 360° Panos! Chandan Yeshwanth &amp; 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 Code

📢DNF: 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.

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!

Check out Alexey Bokhovkin's Mesh2Tex! From a real-world image and a shape mesh to texture, we generate high-res and realistic texturing without requiring any matching geometry or pose alignment to the image! w/ @shubtuls #ICCV2023

Videos

Watch Anya Live

📢WorldMesh is accepted to #ECCV2026, and we're releasing the code today! 🎉 Led by mschneider456: navigable, multi-room 3D scenes from a text prompt, with a mesh scaffold conditioning image diffusion for global consistency + photorealistic detail 👇

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.

Image &amp; video synthesis struggle with the scale of truly large 3D scenes. mschneider456 presents a geometry-first approach : - structure first: mesh scaffold defining the scene - then appearance: mesh-conditioned image synthesis Check it out:

📢Diff3r: fast feed-forward 3DGS + per-scene optimization Yueh-Cheng Liu predicts optimization-ready 3DGS init end to end, computing implicit gradients via Implicit Function Theorem + Gauss-Newton approximation for fast &amp; stable results Check it out:

Excited to share HOI-PAGE, to appear at #ICML2026! 🚀 Lei Li generates 4D human-object interactions zero-shot from text A part-affordance graph grounds interactions via LLM+video priors, enabling complex multi-person, multi-object interactions 👉

Excited to announce ScanNet++ v2!🎉 Chandan Yeshwanth and Yueh-Cheng Liu have been working tirelessly to bring: 🔹1006 high-fidelity 3D scans 🔹+ DSLR &amp; iPhone captures 🔹+ rich semantics Elevating 3D scene understanding to the next level!🚀 w/ Matthias Niessner

📢 QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization Yueh-Cheng Liu learns 2DGS initialization, densification, and optimization priors from ScanNet++ =&gt; fast &amp; accurate reconstruction! Project:

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

📢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:

📢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:

Excited to present DrivAerNet++, coming to #NeurIPS24 Datasets &amp; Benchmarks! DrivAerNet++ introduces the first large-scale multimodal dataset for aerodynamic car design with full CFD simulations. Great work by Mohamed Elrefaie, Florin Morar, Faez Ahmed

📢ScanEdit: Hierarchically-Guided Functional 3D Scan Editing Edit complex, real-world 3D scans with text -- Mohamed El Amine Boudjoghra combines LLM reasoning with geometric optimization to produce physically plausible, instruction-aligned scene edits Check it out:

🚀Join the 𝐒𝐜𝐚𝐧𝐍𝐞𝐭++ 𝐂𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞 #CVPR2026 2025! Think your method can handle large-scale 3D scenes? Put it to the test: Updates: ✅ Preprocessed, undistorted DSLR images ✅ 3DGS demo: by Yueh-Cheng Liu, Chandan Yeshwanth

Check out Christian Diller's CG-HOI :) We generate realistic 3D human-object interactions, from object geometry and text description. A key ingredient is explicit modeling of contact, during training and as guidance during inference.

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

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!

Excited to present UnScene3D coming to #CVPR24. David Rozenberszki introduces the first fully unsupervised learned 3D instance segmentation! Using graph cuts over self-supervised features, and self-training for robust &amp; dense masks. by David Rozenberszki, w/ Or Litany

Looking for a challenging dataset for novel view synthesis and 3D semantics? Check out ScanNet++ at #ICCV23 (Oral)! 460+ scenes w/ 1mm laser scans, semantics, DSLR images, iPhone RGBD video Chandan Yeshwanth Yueh-Cheng Liu Matthias Niessner

📢New in ScanNet++: High-Res 360° Panos! Chandan Yeshwanth & 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 Code

Image & video synthesis struggle with the scale of truly large 3D scenes. mschneider456 presents a geometry-first approach : - structure first: mesh scaffold defining the scene - then appearance: mesh-conditioned image synthesis Check it out:

📢Diff3r: fast feed-forward 3DGS + per-scene optimization Yueh-Cheng Liu predicts optimization-ready 3DGS init end to end, computing implicit gradients via Implicit Function Theorem + Gauss-Newton approximation for fast & stable results Check it out:

Excited to announce ScanNet++ v2!🎉 Chandan Yeshwanth and 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/ Matthias Niessner

📢 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:

Excited to present DrivAerNet++, coming to #NeurIPS24 Datasets & Benchmarks! DrivAerNet++ introduces the first large-scale multimodal dataset for aerodynamic car design with full CFD simulations. Great work by Mohamed Elrefaie, Florin Morar, Faez Ahmed

📢 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:

Excited to present UnScene3D coming to #CVPR24. David Rozenberszki introduces the first fully unsupervised learned 3D instance segmentation! Using graph cuts over self-supervised features, and self-training for robust & dense masks. by David Rozenberszki, w/ Or Litany