# Path-Restore: Learning Network Path Selection for Image Restoration

## TL;DR

Path-Restore introduces a dynamic multi-path CNN with reinforcement learning to adaptively select processing routes for different image regions, improving efficiency and performance in image restoration tasks.

## Contribution

It proposes a novel pathfinder mechanism with reinforcement learning for adaptive route selection in CNNs, reducing computational cost while maintaining or improving restoration quality.

## Key findings

- Achieves comparable or better performance than existing methods.
- Runs 2.7 times faster than RIDNet on real-world denoising.
- Effective in handling spatially varying noise distributions.

## 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, our method achieves comparable performance and runs 2.7x faster on the realistic Darmstadt Noise Dataset.