[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

An open source python package for super-resolution/recovery quality evaluation of hyperspectral images, including RMSE, ERGAS, SSIM, RSNR, PSNR, CC, DD, and SAM.

📈 Implementation of eight evaluation metrics to access the similarity between two images. The eight metrics are as follows: RMSE, PSNR, SSIM, ISSM, FSIM, SRE, SAM, and UIQ.

Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video”

[WACV 2024] Separable Self and Mixed Attention Transformers for Efficient Object Tracking

Official implementation of the paper "DeblurDiNAT: A Generalizable Transformer for Perceptual Image Deblurring".

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

LLM inference in C/C++

This the repo for the paper tiltled "AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation"

A curated list of resources for Image and Video Deblurring

Global Tracking Transformers, CVPR 2022

[AAAI 2024] UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation. UCMCTrack achieves SOTA on MOT17 using estimated camera parameters.

(2019)Visual object tracking based on correlation filtering

code for "CFTracker: Multi-Object Tracking With Cross-Frame Connections in Satellite Videos"

[ICCV2023] MixSort: The Customized Tracker in SportsMOT

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

code for CVPR2024 paper: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction

TransMDOT

An official implementation of Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

deep learning for image processing including classification and object-detection etc.

The state-of-the-art image restoration model without nonlinear activation functions.

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

Yolo X, v7, v8 and several Multi-Object Tracker(SORT, DeepSORT, ByteTrack, BoT-SORT, etc.) in MOT17 and VisDrone2019 Dataset. It uses a unified style and integrated tracker for easy embedding in yo…

This repo is an implementation of PyTorch version YOLOV Series

[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs