Highlights
- Pro
Stars
Ripser++: GPU-accelerated computation of Vietoris–Rips persistence barcodes
Isaac for Healthcare reference workflows
Topological Sculpting of 3D Fine-grained Tubular Shapes
Collection of awesome test-time (domain/batch/instance) adaptation methods
LesionLocator is a framework for zero-shot lesion segmentation and longitudinal tumor tracking in 3D full-body imaging.
Code for CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy
Code for "Generalised Implicit Neural Representations" (NeurIPS 2022).
[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations
Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)
ICML 2025 Spotlight, PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs
The supplementary code for the pulmonary artery-vein segmentation with various inter-slice thickness
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
[ICLR‘25 Spotlight] LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models
An end-to-end framework for pulmonary airway analysis
Automatic differentiation through persistence diagrams with PyTorch
SGLang is a fast serving framework for large language models and vision language models.
My learning notes/codes for ML SYS.
A fast medical imaging analysis library in Python with algorithms for registration, segmentation, and more.
TTK - Topological Data Analysis and Visualization - Source Code
A high-performance topological machine learning toolbox in Python
awesome-topology-driven-deep-image-analysis
[MedIA‘25] Efficient anatomical labeling of pulmonary tree structures via deep point-graph representation-based implicit fields
nnInteractive is a framework for 3D interactive segmentation, supporting intuitive prompts like points, scribbles, bounding boxes, and lasso. Trained on 120+ diverse 3D datasets, it sets a new stan…