https://github.com/syy-whu/drd-net
공식 코드Detail-recovery Image Deraining via Dual Sample-augmented Contrastive Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Detail-recovery Image Deraining via Dual Sample-augmented Contrastive Learning
Semi-MoreGAN: A New Semi-supervised Generative Adversarial Network for Mixture of Rain Removal
EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining
Degradation-Aware Feature Perturbation for All-in-One Image Restoration
Cross-Stitched Multi-task Dual Recursive Networks for Unified Single Image Deraining and Desnowing
Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration
Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey
Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution
DRT: A Lightweight Single Image Deraining Recursive Transformer
MCW-Net: Single Image Deraining with Multi-level Connections and Wide Regional Non-local Blocks
Rain Removal from Light Field Images with 4D Convolution and Multi-scale Gaussian Process
Unsupervised Deraining: Where Contrastive Learning Meets Self-similarity
From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal
Joint Depth Estimation and Mixture of Rain Removal From a Single Image
Semi-Supervised Video Deraining with Dynamical Rain Generator
Exploiting Regional Information Transformer for Single Image Deraining
Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
Restormer: Efficient Transformer for High-Resolution Image Restoration
Progressive Image Deraining Networks: A Better and Simpler Baseline
Image De-raining Using a Conditional Generative Adversarial Network
Residual Squeeze-and-Excitation Network for Fast Image Deraining
Progressive Image Deraining Networks: A Better and Simpler Baseline
Restormer: Efficient Transformer for High-Resolution Image Restoration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.