PromptIR: Prompting for All-in-One Blind Image Restoration [NeurIPS 2023]

深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

[ECCV'24] MetaWeather: Few-Shot Weather-Degraded Image Restoration

[ECCV 2024] OneRestore: A Universal Restoration Framework for Composite Degradation

The official implementation of "Efficient Frequency-Domain Image Deraining with Contrastive Regularization" 【ECCV2024】

Code for Multi-weather Image Restoration via Domain Translation-ICCV 2023

FudanCourtReservation 是一个用于自动预约复旦体育场馆（如羽毛球，网球等）的 Python 脚本

PR2024 GDB: Gated convolutions-based Document Binarization. This repository comprehensively collects the datasets that may be used in document binarization.

Official implementation of MagicFace: Training-free Universal-Style Human Image Customized Synthesis.

MambaOut: Do We Really Need Mamba for Vision?

A PyTorch implementation of ACRNet based on ICME 2023 paper "Weakly-supervised Temporal Action Localization with Adaptive Clustering and Refining Network"

ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation (ICME 2024 oral)

the official repo of the paper Fine-Grained Scene Image Classification with Modality-Agnostic Adapter to appear in ICME 2024.

[ICASSP2024] An official implement of the paper "EFFICIENT SCENE TEXT IMAGE SUPER-RESOLUTION WITH SEMANTIC GUIDANCE"

[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

Official PyTorch Code and Models of "Minutes to Seconds: Speeded-up DDPM-based Image Inpainting with Coarse-to-Fine Sampling", ICME 2024

Official repository of “DDT: Dual-branch Deformable Transformer for Image Denoising, ICME23”

CVPR and NeurIPS poster examples and templates. May we have in-person poster session soon!

Poster Templates (PPT and LaTeX)

Quick scripts to calculate CLIP text-image similarity

The official pytorch implementation of Paper: RECOGNITION-GUIDED DIFFUSION MODEL FOR SCENE TEXT IMAGE SUPER-RESOLUTION

A comprehensive list of awesome document image rectification papers.

Tesseract Open Source OCR Engine (main repository)

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

PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

6.S081课程全记录，包括课程使用的书籍、论文、实验要求的中文翻译，以及实验过程记录

Papers, Datasets, Algorithms, SOTA for STR. Long-time Maintaining