https://github.com/ZhendongWang6/Uformer
공식 코드Uformer: A General U-Shaped Transformer for Image Restoration
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image Enhancement is basically improving the interpretability or perception of information in images for human viewers and providing ‘better’ input for other automated image processing techniques. The principal objective of Image Enhancement is to modify attributes of an image to make it more suitable for a given task and a specific observer.
Source: A Comprehensive Review of Image Enhancement Techniques
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Uformer: A General U-Shaped Transformer for Image Restoration
Retinal Image Restoration using Transformer and Cycle-Consistent Generative Adversarial Network
Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping
Image Super-Resolution as a Defense Against Adversarial Attacks
R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
A Practical Framework for Unsupervised Structure Preservation Medical Image Enhancement
LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancement
Nighttime Person Re-Identification via Collaborative Enhancement Network with Multi-domain Learning
FDCE-Net: Underwater Image Enhancement with Embedding Frequency and Dual Color Encoder
Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image Enhancement
Controlling Vision-Language Models for Multi-Task Image Restoration
Harnessing Multi-resolution and Multi-scale Attention for Underwater Image Restoration
Underwater Object Detection Enhancement via Channel Stabilization
Adaptive deep learning framework for robust unsupervised underwater image enhancement
Conditional Consistency Guided Image Translation and Enhancement
FLIGHT Mode On: A Feather-Light Network for Low-Light Image Enhancement
RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement
Style Generator Inversion for Image Enhancement and Animation
Underwater Image Enhancement with Physical-based Denoising Diffusion Implicit Models
Geometry of the Visual Cortex with Applications to Image Inpainting and Enhancement
Improving Underwater Visual Tracking With a Large Scale Dataset and Image Enhancement
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
DMFourLLIE: Dual-Stage and Multi-Branch Fourier Network for Low-Light Image Enhancement
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.