Starred repositories
Curate, Annotate, and Manage Your Data in LightlyStudio.
Code for "Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates", SIGGRAPH2025
Code for 'DiffuMeta: Algebraic Language Models for Inverse Design of Metamaterials via Diffusion Transformers'
Official Code for "GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training" (ICML 2026) https://arxiv.org/pdf/2602.20399
[CVPR 2026] Offical implementation of PhysGen: Physically Grounded 3D Shape Generation for Industrial Design
The code and dataset for Boundary Representation Transformer
PyTopo3D: 3D SIMP Topology Optimization Framework for Python
We propose VecSet-Edit a pipeline that enable effecive mesh asset editing using single image.
Official inference repo for FLUX.2 models
[CVPR 2026 Oral] A training-free, mask-free framework for 3D shape editing.
[ICLR 2026] NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks
[3DV 2026 Oral] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
Code for [RA-L] High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting
[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
[SIGGRAPH Asia 2023] Learning Contact Deformations with General Collider Descriptors
[NeurIPS 2025] Gaussian-Augmented Physics Simulation and Identification with Complex Colliders
[ICLR 2025] OmniPhysGS: 3D Constitutive Gaussians for General Physics-based Dynamics Generation
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
[ICCV 2025] NormalCrafter: Learning Temporally Consistent Video Normal from Video Diffusion Priors
Awesome 3D Stylization - Advances in 3D Neural Stylization
Identity-preserving 3D geometric stylization via surface normal deformation
[ICCV 2025] DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness
Physically Compatible 3D Object Modeling from a Single Image
[NeurIPS 2024] Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
PhysiOpt: Physics-Driven Shape Optimization for 3D Generative Models
A tool for efficient semi-supervised video object segmentation (great results with minimal manual labor) and a dataset for benchmarking
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2026/ECCV2024 AIGC