https://github.com/tencentarc/mm-realsr
공식 코드MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image Restoration is a family of inverse problems for obtaining a high quality image from a corrupted input image. Corruption may occur due to the image-capture process (e.g., noise, lens blur), post-processing (e.g., JPEG compression), or photography in non-ideal conditions (e.g., haze, motion blur).
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution
Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration
Zero-Shot Image Restoration Using Few-Step Guidance of Consistency Models (and Beyond)
Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance
Emphasizing Crucial Features for Efficient Image Restoration
Enhancing Image Restoration through Learning Context-Rich and Detail-Accurate Features
Sequential Gating Ensemble Network for Noise Robust Multi-Scale Face Restoration
Image Restoration by Iterative Denoising and Backward Projections
Distilled Pooling Transformer Encoder for Efficient Realistic Image Dehazing
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
Degradation-Aware Feature Perturbation for All-in-One Image Restoration
FaceQgen: Semi-Supervised Deep Learning for Face Image Quality Assessment
Improving Super-Resolution Performance using Meta-Attention Layers
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control
Deep Atrous Guided Filter for Image Restoration in Under Display Cameras
Cross-Stitched Multi-task Dual Recursive Networks for Unified Single Image Deraining and Desnowing
Chasing Better Deep Image Priors between Over- and Under-parameterization
Physics-Driven Turbulence Image Restoration with Stochastic Refinement
DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows
Microscopy Image Restoration with Deep Wiener-Kolmogorov filters
Implicit Image-to-Image Schrodinger Bridge for Image Restoration
Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.