-
Technical University Munich
- Munich
- https://daoyig.github.io/
Highlights
- Pro
Stars
Roblox Foundation Model for 3D Intelligence
WorldGrow: Generating Infinite 3D World [AAAI 2026 Oral]
An end-to-end open ecosystem for robot learning
Masked Depth Modeling for Spatial Perception
A simulation platform for versatile Embodied AI research and developments.
Native and Compact Structured Latents for 3D Generation
[CVPR 2026] Official Implementation of Particulate: Feed-Forward 3D Object Articulation
Simple 3d mapping and physic simulation on blender
High-quality and editable surfel 3D Gaussian generation through native 3D diffusion (ICLR 2025)
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
A collection of unusual mesh processing algorithms.
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image (CVPR 2026)
[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
LL3M writes Python code that generates 3D assets in Blender.
Python efficient farthest point sampling (FPS) library. Compatible with numpy.
[CVPR 2026 (Oral)] Official Torch/CUDA Implementation of Faithful Contouring
Code for RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching
PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)
A part-based 3D generation framework & the largest and most comprehensively annotated 3D part dataset.