[CVPR 2025] ProtoDepth: Unsupervised Continual Depth Completion with Prototypes

Implementation of Focal Loss (Lin et al., 2017, Facebook AI Research) for handling class imbalance by focusing learning on hard, misclassified examples.

Learning Self-Supervised Representations for Label Efficient Cross-Domain Knowledge Transfer on Diabetic Retinopathy Fundus Images (IJCNN 2023)

Diffusion Model docker

Repository of paper Consistency-preserving Visual Question Answering in Medical Imaging (MICCAI2022)

Offical codebase repository for the ECCV 2024 paper titled "UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework"

[ECCV 2024] Official implementation of "Uncertainty Calibration with Energy Based Instance-wise Scaling in the Wild Dataset"

Code for the paper "Where are we with calibration under dataset shift in image classification?"

PyTorch Implementation of Spiking Transformer with Spatial-Temporal Attention (CVPR 2025)

Vision Foundation Models for Medical AI, including RETFound, DINOv2, DINOv3

Robust fine-tuning of zero-shot models

[CVPR 2025] Custom Open CLIP repo to train biomedical CLIP models

[CVPR 2025] BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

[ICCV 2025] Zero-Shot Monocular Depth Completion with Guided Diffusion

Collaborative Highway Asset Research: Integrated Sensor-Modeling Application (CHARISMA) is a collaborative platform collaborative analysis and visualization of NDE and other infrastructure data and…

Visual Odometry with Inertial and Depth (VOID) dataset

[CVPR 2024] TEA: Test-time Energy Adaptation

[NeurIPS 2024 - Spotlight] Transduction for Vision-Language Models (TransCLIP): code for the paper "Boosting Vision-Language Models with Transduction".

[ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes

Submanifold sparse convolutional networks

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

Spatial Sparse Convolution Library

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)