https://github.com/iridescentttt/SynQT
MambaIR: A Simple Baseline for Image Restoration with State-Space Model
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.
MambaIR: A Simple Baseline for Image Restoration with State-Space Model
Soft Prototyping Camera Designs for Car Detection Based on a Convolutional Neural Network
Enhanced Deep Residual Networks for Single Image Super-Resolution
AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion
Uformer: A General U-Shaped Transformer for Image Restoration
On learning optimized reaction diffusion processes for effective image restoration
Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
Interpretable Unsupervised Diversity Denoising and Artefact Removal
Cryo-CARE: Content-Aware Image Restoration for Cryo-Transmission Electron Microscopy Data
Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding
Enhanced Deep Residual Networks for Single Image Super-Resolution
EnlightenGAN: Deep Light Enhancement without Paired Supervision
Deep Network Interpolation for Continuous Imagery Effect Transition
Enhanced Deep Residual Networks for Single Image Super-Resolution
Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
Restormer: Efficient Transformer for High-Resolution Image Restoration
Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.