# Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring

arXiv: https://arxiv.org/abs/2104.12665 · HTML: https://mlsanity.com/paper/2104.12665/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 59 references that are in the map.
- First posted on arXiv 26 Apr 2021.

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020)
- [Human-Aware Motion Deblurring](https://mlsanity.com/paper/2001.06816/) (2020)
- [The 2018 PIRM Challenge on Perceptual Image Super-resolution](https://mlsanity.com/paper/1809.07517/) (2018)
- [Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal](https://mlsanity.com/paper/1503.00593/) (2015)
- [Detail-revealing Deep Video Super-resolution](https://mlsanity.com/paper/1704.02738/) (2017)
- [Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring](https://mlsanity.com/paper/2004.05343/) (2020)
- [Neural Blind Deconvolution Using Deep Priors](https://mlsanity.com/paper/1908.02197/) (2019)
- [Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training](https://mlsanity.com/paper/1911.07410/) (2019)
- [From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur](https://mlsanity.com/paper/1612.02583/) (2016)
- [Learning to Deblur](https://mlsanity.com/paper/1406.7444/) (2014)
- [A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model](https://mlsanity.com/paper/2006.15057/) (2020)
- [Reblur2Deblur: Deblurring Videos via Self-Supervised Learning](https://mlsanity.com/paper/1801.05117/) (2018)
- [Learning to Synthesize Motion Blur](https://mlsanity.com/paper/1811.11745/) (2018)
- [Projected Distribution Loss for Image Enhancement](https://mlsanity.com/paper/2012.09289/) (2020)
- [Maintaining Natural Image Statistics with the Contextual Loss](https://mlsanity.com/paper/1803.04626/) (2018)
- [Motion Deblurring in the Wild](https://mlsanity.com/paper/1701.01486/) (2017)

## Built on by (most cited first, 17 of 17)

- [InstructIR: High-Quality Image Restoration Following Human Instructions](https://mlsanity.com/paper/2401.16468/) (2024)
- [PromptIR: Prompting for All-in-One Blind Image Restoration](https://mlsanity.com/paper/2306.13090/) (2023)
- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [Multiscale Structure Guided Diffusion for Image Deblurring](https://mlsanity.com/paper/2212.01789/) (2022)
- [UniProcessor: A Text-induced Unified Low-level Image Processor](https://mlsanity.com/paper/2407.20928/) (2024)
- [ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation](https://mlsanity.com/paper/2312.10998/) (2023)
- [Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective](https://mlsanity.com/paper/2303.06859/) (2023)
- [Attentive Fine-Grained Structured Sparsity for Image Restoration](https://mlsanity.com/paper/2204.12266/) (2022)
- [Image Deblurring by Exploring In-depth Properties of Transformer](https://mlsanity.com/paper/2303.15198/) (2023)
- [INFWIDE: Image and Feature Space Wiener Deconvolution Network for Non-blind Image Deblurring in Low-Light Conditions](https://mlsanity.com/paper/2207.08201/) (2022)
- [Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration](https://mlsanity.com/paper/2404.02154/) (2024)
- [Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization](https://mlsanity.com/paper/2404.12168/) (2024)
- [Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration](https://mlsanity.com/paper/2506.21722/) (2025)
- [Lightweight High-Speed Photography Built on Coded Exposure and Implicit Neural Representation of Videos](https://mlsanity.com/paper/2311.13134/) (2023)
- [CAR-Net: A Cascade Refinement Network for Rotational Motion Deblurring under Angle Information Uncertainty](https://mlsanity.com/paper/2512.00700/) (2025)
- [EvBS: Event-guided Blur Synthesis for Domain-adaptive Motion Deblurring](https://mlsanity.com/paper/2608.08066/) (2026)
- [Dynamic Time Step Prediction in Inverse Heat Dissipation for Blur-Like Image Restoration Tasks](https://mlsanity.com/paper/2610.03942/) (2026)

## Abstract (arXiv)

The goal of dynamic scene deblurring is to remove the motion blur in a given image. Typical learning-based approaches implement their solutions by minimizing the L1 or L2 distance between the output and the reference sharp image. Recent attempts adopt visual recognition features in training to improve the perceptual quality. However, those features are primarily designed to capture high-level contexts rather than low-level structures such as blurriness. Instead, we propose a more direct way to make images sharper by exploiting the inverse task of deblurring, namely, reblurring. Reblurring amplifies the remaining blur to rebuild the original blur, however, a well-deblurred clean image with zero-magnitude blur is hard to reblur. Thus, we design two types of reblurring loss functions for better deblurring. The supervised reblurring loss at training stage compares the amplified blur between the deblurred and the sharp images. The self-supervised reblurring loss at inference stage inspects if there noticeable blur remains in the deblurred. Our experimental results on large-scale benchmarks and real images demonstrate the effectiveness of the reblurring losses in improving the perceptual quality of the deblurred images in terms of NIQE and LPIPS scores as well as visual sharpness.