Stars
Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces
Learning Continuous Signed Distance Functions for Shape Representation
Papers and Datasets about Point Cloud.
This is a skeleton vault of my Obsidian Ph.D. Vault that I use for work.
[CVPR 2025 Award Candidate & Oral] TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion
Implementation of paper "Uni-3DAR: Unified 3D Generation and Understanding via Autoregression on Compressed Spatial Tokens"
Tool for robust segmentation of >100 important anatomical structures in CT images
[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration
TorchCFM: a Conditional Flow Matching library
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.
A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…
[ACM CSUR 2025] Understanding World or Predicting Future? A Comprehensive Survey of World Models
point cloud datasets which contains various types of bone
Official implementation of Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model
Simulating the Real World: Survey & Resources, which contains our survey "Simulating the Real World: A Unified Survey of Multimodal Generative Models" and Awesome-Text2X-Resources. Watch this repos…
Native and Compact Structured Latents for 3D Generation
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction
collect papers about human motion capture
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation (Accepted by NeurIPS-2023)
Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)
A fast and robust point cloud registration library
Go-ICP for globally optimal 3D pointset registration
A Blender addon for generating synthetic ground truth data for Computer Vision applications
ComfyUI wrapper for Motion capture from video
[ICCV2025] GARF: Learning Generalizable 3D Reassembly for Real-World Fractures