# Exploring and Evaluating Image Restoration Potential in Dynamic Scenes

arXiv: https://arxiv.org/abs/2203.11754 · HTML: https://mlsanity.com/paper/2203.11754/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 22 Mar 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Real Image Denoising with Feature Attention](https://mlsanity.com/paper/1904.07396/) (2019)
- [MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2004.05508/) (2020)
- [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020)
- [Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation](https://mlsanity.com/paper/2003.13045/) (2020)
- [From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur](https://mlsanity.com/paper/1612.02583/) (2016)
- [Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising](https://mlsanity.com/paper/1705.09912/) (2017)
- [Low-light Image Restoration with Short- and Long-exposure Raw Pairs](https://mlsanity.com/paper/2007.00199/) (2020)
- [Attention-based network for low-light image enhancement](https://mlsanity.com/paper/2005.09829/) (2020)
- [Digital Gimbal: End-to-end Deep Image Stabilization with Learnable Exposure Times](https://mlsanity.com/paper/2012.04515/) (2020)
- [Non-uniform Motion Deblurring with Blurry Component Divided Guidance](https://mlsanity.com/paper/2101.06021/) (2021)

## Built on by (most cited first, 8 of 8)

- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [Towards Open-ended Visual Quality Comparison](https://mlsanity.com/paper/2402.16641/) (2024)
- [All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation](https://mlsanity.com/paper/2308.03021/) (2023)
- [Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs](https://mlsanity.com/paper/2402.07116/) (2024)
- [Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy](https://mlsanity.com/paper/2503.20673/) (2025)
- [Non-Uniform Exposure Imaging via Neuromorphic Shutter Control](https://mlsanity.com/paper/2404.13972/) (2024)
- [Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment](https://mlsanity.com/paper/2411.09007/) (2024)
- [Dual-Exposure Imaging with Events](https://mlsanity.com/paper/2604.10273/) (2026)

## Abstract (arXiv)

In dynamic scenes, images often suffer from dynamic blur due to superposition of motions or low signal-noise ratio resulted from quick shutter speed when avoiding motions. Recovering sharp and clean results from the captured images heavily depends on the ability of restoration methods and the quality of the input. Although existing research on image restoration focuses on developing models for obtaining better restored results, fewer have studied to evaluate how and which input image leads to superior restored quality. In this paper, to better study an image's potential value that can be explored for restoration, we propose a novel concept, referring to image restoration potential (IRP). Specifically, We first establish a dynamic scene imaging dataset containing composite distortions and applied image restoration processes to validate the rationality of the existence to IRP. Based on this dataset, we investigate several properties of IRP and propose a novel deep model to accurately predict IRP values. By gradually distilling and selective fusing the degradation features, the proposed model shows its superiority in IRP prediction. Thanks to the proposed model, we are then able to validate how various image restoration related applications are benefited from IRP prediction. We show the potential usages of IRP as a filtering principle to select valuable frames, an auxiliary guidance to improve restoration models, and even an indicator to optimize camera settings for capturing better images under dynamic scenarios.