Spatially-Adaptive Image Restoration using Distortion-Guided Networks

by   Kuldeep Purohit, et al.

We present a general learning-based solution for restoring images suffering from spatially-varying degradations. Prior approaches are typically degradation-specific and employ the same processing across different images and different pixels within. However, we hypothesize that such spatially rigid processing is suboptimal for simultaneously restoring the degraded pixels as well as reconstructing the clean regions of the image. To overcome this limitation, we propose SPAIR, a network design that harnesses distortion-localization information and dynamically adjusts computation to difficult regions in the image. SPAIR comprises of two components, (1) a localization network that identifies degraded pixels, and (2) a restoration network that exploits knowledge from the localization network in filter and feature domain to selectively and adaptively restore degraded pixels. Our key idea is to exploit the non-uniformity of heavy degradations in spatial-domain and suitably embed this knowledge within distortion-guided modules performing sparse normalization, feature extraction and attention. Our architecture is agnostic to physical formation model and generalizes across several types of spatially-varying degradations. We demonstrate the efficacy of SPAIR individually on four restoration tasks-removal of rain-streaks, raindrops, shadows and motion blur. Extensive qualitative and quantitative comparisons with prior art on 11 benchmark datasets demonstrate that our degradation-agnostic network design offers significant performance gains over state-of-the-art degradation-specific architectures. Code available at



There are no comments yet.


page 1

page 4

page 7

page 8


Image Restoration using Feature-guidance

Image restoration is the task of recovering a clean image from a degrade...

Attention Prior for Real Image Restoration

Deep convolutional neural networks perform better on images containing s...

Spatially-Adaptive Residual Networks for Efficient Image and Video Deblurring

In this paper, we address the problem of dynamic scene deblurring in the...

LIRA: Lifelong Image Restoration from Unknown Blended Distortions

Most existing image restoration networks are designed in a disposable wa...

Semantic Image Synthesis with Spatially-Adaptive Normalization

We propose spatially-adaptive normalization, a simple but effective laye...

Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network

In recent years, deep learning-based methods have been successfully appl...

Ink removal from histopathology whole slide images by combining classification, detection and image generation models

Histopathology slides are routinely marked by pathologists using permane...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.