PyTorch code and models for the DINOv2 self-supervised learning method.

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

Segment Anything in Medical Images

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

Segment Anything 2 for Surgical Video Segmentation

[SIGGRAPH'24] A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose

Scikit-learn compatible decision trees beyond those offered in scikit-learn

Endoscopy Specular Reflection Removal

Ongoing project. Detecting blind spots on colonoscopic surfaces.