[ICCV2025] SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning. Paper is available at https://arxiv.org/abs/2410.14987

SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation

A lightweight LMM-based Document Parsing Model

UMatcher: A modern template matching model

[CVPR 2024] PEM: Prototype-based Efficient MaskFormer for Image Segmentation

TPAMI：Frequency-aware Feature Fusion for Dense Image Prediction

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models

Lightweight workflow engine for .NET Standard

This repository is an official implementation of the paper "LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection".

Official repository of Agent Attention (ECCV2024)

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.

the official pytorch implementation of “Mamba-YOLO：SSMs-based for Object Detection”

Character Animation (AnimateAnyone, Face Reenactment)

Code for paper LocalMamba: Visual State Space Model with Windowed Selective Scan

Official pytorch code of our paper "MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection"

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

[2021CVPR] Adaptive Image Transformer for One-Shot Object Detection

This is the official source for our ICCV 2023 paper "EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation"

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

[ICCV 2023] MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices

Official implementation of SCTNet (AAAI2024)

Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models

U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

Unofficial implementation of Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Unofficial re-implementation of MemSeg for Anomaly Detection