-
Tsinghua University
- Beijing, China
- https://jeffreyxiang.github.io/
Stars
official code of “OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding”
Official Torch/CUDA Implementation of Faithful Contouring
[PG2025] PaMO: Parallel Mesh Optimization for Intersection-Free Low-Poly Modeling on the GPU
Python library for loading and using triangular meshes.
UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation
Make your wildest 3D ConvNet dream architectures come true
Reference PyTorch implementation and models for DINOv3
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
Official Repo of TexVerse: A Universe of 3D Objects with High-Resolution Textures
[ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy
[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding
Official Code Release for [SIGGRAPH 2025] RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
[NeurIPS 2025] Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
A Modular Framework for 3D Generation and Beyond [WIP]
SynCity: Training-Free Generation of 3D Worlds
Batch computation of the linear assignment problem on GPU.
Roblox Foundation Model for 3D Intelligence
[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
[CVPR 2025] TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing
Unleashing Vecset Diffusion Model for Fast Shape Generation / within 1 Second (ICCV'25 Highlight)
[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation