[ECCV 2024] LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow

Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包，支持亿级数据文搜文、文搜图、图搜图，python3开发，开箱即用。

📝Awesome and classical image retrieval papers

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

Multiple object tracking using Kalman Filter and Hungarian Algorithm - OpenCV

动态语义SLAM 目标检测+VSLAM+光流/多视角几何动态物体检测+octomap地图+目标数据库

The official implementation of the ECCV 2022 Oral paper: RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos

[NeurIPS2021] BOVText: A Large-Scale, Multidimensional Multilingual Dataset for Video Text Spotting

This is a list of awesome paper about optical flow and related work.

Dense matching library based on PyTorch

Resources for Multiple Object Tracking (MOT)

A personal list of papers and resources of image matching and pose estimation, including perspective images and panoramas.

[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

one summary of diffusion-based image processing, including restoration, enhancement, coding, quality assessment

ACM Multimedia 2023: DocDiff: Document Enhancement via Residual Diffusion Models. Also contains 1597 red seals in Chinese scenes, along with their corresponding binary masks.

Image Restoration with Mean-Reverting Stochastic Differential Equations, ICML 2023. Winning solution of the NTIRE 2023 Image Shadow Removal Challenge.

Collect super-resolution related papers, data, repositories

A curated list of image inpainting and video inpainting papers and resources

A playbook for systematically maximizing the performance of deep learning models.

[NeurIPS 2022] Denoising Diffusion Restoration Models -- Official Code Repository

D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration. ECCV, 2022

Self-Supervised Image Denoising via Iterative Data Refinement (CVPR2022)

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

Exploring Image Deblurring via Blur Kernel Space (CVPR'21)

Generate authentic motion blur kernels (point spread functions) and apply them to images. Fast and Simple.

A latent text-to-image diffusion model

Taming Transformers for High-Resolution Image Synthesis