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

arXiv: https://arxiv.org/abs/1904.10343 · HTML: https://mlsanity.com/paper/1904.10343/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2019.

## Built on by (most cited first, 30 of 40)

- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021)
- [ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration](https://mlsanity.com/paper/2306.13653/) (2023)
- [Complexity Experts are Task-Discriminative Learners for Any Image Restoration](https://mlsanity.com/paper/2411.18466/) (2024)
- [C2N: Practical Generative Noise Modeling for Real-World Denoising](https://mlsanity.com/paper/2202.09533/) (2022)
- [ReconfigISP: Reconfigurable Camera Image Processing Pipeline](https://mlsanity.com/paper/2109.04760/) (2021)
- [CAMixerSR: Only Details Need More "Attention"](https://mlsanity.com/paper/2402.19289/) (2024)
- [NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer](https://mlsanity.com/paper/2303.06919/) (2023)
- [CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution](https://mlsanity.com/paper/2207.10345/) (2022)
- [See More Details: Efficient Image Super-Resolution by Experts Mining](https://mlsanity.com/paper/2402.03412/) (2024)
- [ARM: Any-Time Super-Resolution Method](https://mlsanity.com/paper/2203.10812/) (2022)
- [RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization](https://mlsanity.com/paper/2205.05671/) (2022)
- [Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration](https://mlsanity.com/paper/2404.00288/) (2024)
- [Multi-Scale Adaptive Network for Single Image Denoising](https://mlsanity.com/paper/2203.04313/) (2022)
- [Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing](https://mlsanity.com/paper/2306.16060/) (2023)
- [Dynamic Attention-Guided Diffusion for Image Super-Resolution](https://mlsanity.com/paper/2308.07977/) (2023)
- [Dynamic Slimmable Denoising Network](https://mlsanity.com/paper/2110.08940/) (2021)
- [AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution](https://mlsanity.com/paper/2404.03296/) (2024)
- [From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm](https://mlsanity.com/paper/2306.06388/) (2023)
- [M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration](https://mlsanity.com/paper/2506.07814/) (2025)
- [Lightweight Stepless Super-Resolution of Remote Sensing Images via Saliency-Aware Dynamic Routing Strategy](https://mlsanity.com/paper/2210.07598/) (2022)
- [Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration](https://mlsanity.com/paper/2401.13221/) (2024)
- [A Preliminary Exploration Towards General Image Restoration](https://mlsanity.com/paper/2408.15143/) (2024)
- [Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network](https://mlsanity.com/paper/2009.14563/) (2020)
- [Devil is in the Uniformity: Exploring Diverse Learners within Transformer for Image Restoration](https://mlsanity.com/paper/2503.20174/) (2025)
- [R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery](https://mlsanity.com/paper/2107.05318/) (2021)
- [Robust Deep Ensemble Method for Real-world Image Denoising](https://mlsanity.com/paper/2206.03691/) (2022)
- [Learning Where and What to Restore for Composite Image Restoration](https://mlsanity.com/paper/2503.17915/) (2025)
- [Towards Unified Image Deblurring using a Mixture-of-Experts Decoder](https://mlsanity.com/paper/2508.06228/) (2025)

## Abstract (arXiv)

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.