Paper Info
Title
Path-Restore: Learning Network Path Selection for Image Restoration
Abstract
Very deep Convolutional Neural Networks (CNNs) have greatly improved the performance on various image restoration tasks. However, this comes at a price of increasing computational burden, hence limiting their practical usages. We observe that some corrupted image regions are inherently easier to restore than others since the distortion and content vary within an image. To leverage this, we propose Path-Restore, a multi-path CNN with a pathfinder that can dynamically select an appropriate route for each image region. We train the pathfinder using reinforcement learning with a difficulty-regulated reward. This reward is related to the performance, complexity and “the difficulty of restoring a region”. A policy mask is further investigated to jointly process all the image regions. We conduct experiments on denoising and mixed restoration tasks. The results show that our method achieves comparable or superior performance to existing approaches with less computational cost. In particular, Path-Restore is effective for real-world denoising, where the noise distribution varies across different regions on a single image. Compared to the state-of-the-art RIDNet [1], our method achieves comparable performance and runs 2.7x faster on the realistic Darmstadt Noise Dataset [2]. Models and codes are available on the project page: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://www.mmlab-ntu.com/project/pathrestore/</uri> .
Year
DOI
Venue
2019
10.1109/TPAMI.2021.3096255
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords
DocType
Volume
Algorithms,Image Processing, Computer-Assisted,Neural Networks, Computer,Signal-To-Noise Ratio
Journal
44
Issue
ISSN
Citations 
10
0162-8828
2
PageRank 
References 
Authors
0.38
15
5
Name
Order
Citations
PageRank
Ke Yu115218.85
Xintao Wang21449.14
Chao Dong3206480.72
Xiaoou Tang415728670.19
Chen Change Loy54484178.56