Highlights
- Pro
Stars
"Neural Attenuation Fields for Sparse-View CBCT Reconstruction" (MICCAI 2022 Oral)
Training patient-specific 2D/3D registration models in 5 minutes
SG2VID: Scene Graphs Enable Fine-Grained Control for Video Synthesis (MICCAI 2025 - ORAL)
A header-only neural network library for microcontrollers, with partial bare-metal & native-os support.
Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures
Some out-of-the-box hooks for pre-commit
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.
Lightweight, general, scalable C++ library for finite element methods
Pytorch code to construct a 3D point cloud model from single RGB image.
[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
Quickstart template for GDExtension development with Godot
[MICCAI'23] Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train
Auto-differentiable digitally reconstructed radiographs in PyTorch
Next-generation Albumentations: dual-licensed for open-source and commercial use
A modern and customizable python UI-library based on Tkinter
PyTorch implementation of normalizing flow models
Inofficial dataset abstraction KvasirCapsule dataset
Artistic style transfer has been part of the quickly growing AI Art community in recent times. Pioneered by Gatys et al this class of methods allows for the transfer of a style, texture, pattern ec…
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Official Implementation of Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling
napari: a fast, interactive, multi-dimensional image viewer for python
🩻 A 3D Slicer plugin for fully automated segmentation of 167 anatomical structures in CT.