Papers with Code 아카이브
Image Restoration
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 13
- 평가표
- 3
- 보존된 평가 기록
- 17
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).
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/caiyuanhao1998/MST
공식 코드Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
https://github.com/caiziruo/nf-ula
공식 코드NF-ULA: Langevin Monte Carlo with Normalizing Flow Prior for Imaging Inverse Problems
https://github.com/calvinyang0/crnet
공식 코드CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task
https://github.com/cameltr/transref
공식 코드TransRef: Multi-Scale Reference Embedding Transformer for Reference-Guided Image Inpainting
https://github.com/cameronfabbri/Underwater-Color-Correction
공식 코드Enhancing Underwater Imagery using Generative Adversarial Networks
https://github.com/caojiezhang/deqir
공식 코드Deep Equilibrium Diffusion Restoration with Parallel Sampling
https://github.com/casus/phirm
공식 코드Phenotype-preserving metric design for high-content image reconstruction by generative inpainting
https://github.com/chaofengc/femasr
공식 코드Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors
https://github.com/chaofengc/quantexsr
공식 코드Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors
https://github.com/charlesmillard/Noisier2Noise_for_recon
공식 코드https://github.com/chdwyb/rsformer
공식 코드Towards an Effective and Efficient Transformer for Rain-by-snow Weather Removal
https://github.com/chengeng0613/hlnet
공식 코드Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition
https://github.com/chengxuliu/ddrnet
공식 코드Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera
https://github.com/chenmingxiang110/VAE-NCA
공식 코드https://github.com/chenzxyz/prob_res_learning
공식 코드Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration
https://github.com/chingheng0808/PromptHSI
공식 코드https://github.com/chongwang1024/rdmd
공식 코드https://github.com/chunminghe/reti-diff
공식 코드Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
https://github.com/cidautai/darkir
공식 코드https://github.com/cig-skoltech/deep_demosaick
공식 코드Iterative Joint Image Demosaicking and Denoising using a Residual Denoising Network
https://github.com/clausy9/bmtnet
공식 코드Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing
https://github.com/climbin/restormixer
공식 코드An Efficient and Mixed Heterogeneous Model for Image Restoration
https://github.com/clovaai/cutblur
공식 코드Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy
https://github.com/cpregroup/specnerf-v2
공식 코드https://github.com/csbhr/Deep-Blind-VSR
공식 코드https://github.com/cschenxiang/drsformer
공식 코드Learning A Sparse Transformer Network for Effective Image Deraining
https://github.com/csdwren/sfarl
공식 코드Simultaneous Fidelity and Regularization Learning for Image Restoration
https://github.com/csguoh/adaptir
공식 코드Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
https://github.com/csguoh/mambair
공식 코드MambaIR: A Simple Baseline for Image Restoration with State-Space Model
https://github.com/csguoh/refir
공식 코드ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
https://github.com/csmliu/pretrained-gans
공식 코드A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration
https://github.com/csslc/ea-adam
공식 코드Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective
https://github.com/cswin/RC-Nets
공식 코드Image Restoration Using Deep Regulated Convolutional Networks
https://github.com/cswry/osediff
공식 코드One-Step Effective Diffusion Network for Real-World Image Super-Resolution
https://github.com/cszhilu1998/bracketire
공식 코드Exposure Bracketing Is All You Need For A High-Quality Image
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.