Depth Anything 3

[CVPR 2026] Official repository for the paper "LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings".

Deep learning-based segmentation framework for automated spleen length measurement from ultrasound images, achieving human-level accuracy with a modified U-Net and PCA-based post-processing.

[ICCV 2025] HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation

An Unsupervised and Training-free Method for Phase Detection in Echocardiography

[CVPR 2025] Learning Flow Fields in Attention for Controllable Person Image Generation

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Official repository of “MatchSeg"

PyTorch implementation for "Rethinking Low-quality Optical Flow in Unsupervised Surgical Instrument Segmentation"

ARHNet: Adaptive Region Harmonization for Lesion-aware Augmentation to Improve Segmentation Performance

The docker submission of team CTRL for ATLAS R2.0 (Anatomical Tracings of Lesions After Stroke Segmentation Challenge)

Long Surgical Phase Recognition

The official code of CornerTransformer (ECCV 2022, Oral) on top of MMOCR.