Stars
Training library for local feature detection and matching
[CVPR'25 Highlight] Multi-modal Vision Pre-training for Medical Image Analysis
Review-Gate V2 is a powerful rule for the Cursor IDE that helps you get up to 5x more value from your monthly requests. It creates an interactive loop where the AI waits for your fol 8000 low-up commands…
[ECCV 2024 Best Paper Candidate] PointLLM: Empowering Large Language Models to Understand Point Clouds
[CVPR 2025] Parallel Sequence Modeling via Generalized Spatial Propagation Network
dcm2nii DICOM to NIfTI converter: compiled versions available from NITRC
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
A generative world for general-purpose robotics & embodied AI learning.
Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.
Interactive visualizations of the geometric intuition behind diffusion models.
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis
GARF: Learning Generalizable 3D Reassembly for Real-World Fractures
[CVPR 2024] Probing the 3D Awareness of Visual Foundation Models
[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations
[CVPR 2025] HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
[AAAI 2025] HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions, PyTorch implementation.
PointPWC-Net is a deep coarse-to-fine network designed for 3D scene flow estimation from 3D point clouds.
NeurIPS 2023 - Lung250M-4B: A Combined 3D Dataset for CT- and Point Cloud-Based Intra-Patient Lung Registration
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.