Image Restoration
467 papers with code • 1 benchmarks • 12 datasets
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).
Libraries
Use these libraries to find Image Restoration models and implementationsDatasets
SIDD
CBSD68
Raindrop
PIRM
TinyPerson
Real Rain Dataset
UHDM
Fingerprint inpainting and denoising
Subtasks
Latest papers
CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task
In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images.
Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition
Specifically, we employ two modules for feature extraction: shared weight modules and non-shared weight modules.
Referring Flexible Image Restoration
These situations and requirements shed light on a new challenge in image restoration, where a model must perceive and remove specific degradation types specified by human commands in images with multiple degradations.
Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models
Though diffusion models have been successfully applied to various image restoration (IR) tasks, their performance is sensitive to the choice of training datasets.
Equipping Diffusion Models with Differentiable Spatial Entropy for Low-Light Image Enhancement
shermanlian/spatial-entropy-loss
•
•
In this work, we propose a novel method that shifts the focus from a deterministic pixel-by-pixel comparison to a statistical perspective, emphasizing the learning of distributions rather than individual pixel values.
TBSN: Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising
For channel self-attention, we observe that it may leak the blind-spot information when the channel number is greater than spatial size in the deep layers of multi-scale architectures.
Unfolding ADMM for Enhanced Subspace Clustering of Hyperspectral Images
By unfolding iterative optimization methods into neural networks, this approach offers enhanced interpretability and reliability compared to data-driven deep learning methods, and greater adaptability and generalization than model-based approaches.
Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration
All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation.
Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
KU-CVLAB/Perturbed-Attention-Guidance
•
•
These techniques are often not applicable in unconditional generation or in various downstream tasks such as image restoration.
SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder
We employ our method to generate paired training samples for real-world image denoising and super-resolution tasks.
