# From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur

arXiv: https://arxiv.org/abs/1612.02583 · HTML: https://mlsanity.com/paper/1612.02583/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2016.

## Built on by (most cited first, 30 of 81)

- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [Deep Generalized Unfolding Networks for Image Restoration](https://mlsanity.com/paper/2204.13348/) (2022)
- [Event-Based Fusion for Motion Deblurring with Cross-modal Attention](https://mlsanity.com/paper/2112.00167/) (2021)
- [LEDNet: Joint Low-light Enhancement and Deblurring in the Dark](https://mlsanity.com/paper/2202.03373/) (2022)
- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks](https://mlsanity.com/paper/2302.08890/) (2023)
- [Spatially-Adaptive Image Restoration using Distortion-Guided Networks](https://mlsanity.com/paper/2108.08617/) (2021)
- [ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring](https://mlsanity.com/paper/2103.04260/) (2021)
- [Motion Deblurring with Real Events](https://mlsanity.com/paper/2109.13695/) (2021)
- [Flow-Guided Sparse Transformer for Video Deblurring](https://mlsanity.com/paper/2201.01893/) (2022)
- [BALF: Simple and Efficient Blur Aware Local Feature Detector](https://mlsanity.com/paper/2211.14731/) (2022)
- [Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion](https://mlsanity.com/paper/2403.13327/) (2024)
- [SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring](https://mlsanity.com/paper/2110.05803/) (2021)
- [Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring](https://mlsanity.com/paper/2112.05150/) (2021)
- [Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes](https://mlsanity.com/paper/2304.08993/) (2023)
- [Spatio-Temporal Deformable Attention Network for Video Deblurring](https://mlsanity.com/paper/2207.10852/) (2022)
- [All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation](https://mlsanity.com/paper/2308.03021/) (2023)
- [FCL-GAN: A Lightweight and Real-Time Baseline for Unsupervised Blind Image Deblurring](https://mlsanity.com/paper/2204.07820/) (2022)
- [Multi-scale frequency separation network for image deblurring](https://mlsanity.com/paper/2206.00798/) (2022)
- [Face Deblurring using Dual Camera Fusion on Mobile Phones](https://mlsanity.com/paper/2207.11617/) (2022)
- [Perceptual Image Enhancement for Smartphone Real-Time Applications](https://mlsanity.com/paper/2210.13552/) (2022)
- [Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring](https://mlsanity.com/paper/2104.12665/) (2021)
- [Efficient Video Deblurring Guided by Motion Magnitude](https://mlsanity.com/paper/2207.13374/) (2022)
- [D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration](https://mlsanity.com/paper/2207.03294/) (2022)
- [Optical Flow Estimation from a Single Motion-blurred Image](https://mlsanity.com/paper/2103.02996/) (2021)
- [Non-uniform Blur Kernel Estimation via Adaptive Basis Decomposition](https://mlsanity.com/paper/2102.01026/) (2021)
- [Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects](https://mlsanity.com/paper/2106.08762/) (2021)
- [Event-based Image Deblurring with Dynamic Motion Awareness](https://mlsanity.com/paper/2208.11398/) (2022)
- [Exploring and Evaluating Image Restoration Potential in Dynamic Scenes](https://mlsanity.com/paper/2203.11754/) (2022)

## Abstract (arXiv)

Removing pixel-wise heterogeneous motion blur is challenging due to the ill-posed nature of the problem. The predominant solution is to estimate the blur kernel by adding a prior, but the extensive literature on the subject indicates the difficulty in identifying a prior which is suitably informative, and general. Rather than imposing a prior based on theory, we propose instead to learn one from the data. Learning a prior over the latent image would require modeling all possible image content. The critical observation underpinning our approach is thus that learning the motion flow instead allows the model to focus on the cause of the blur, irrespective of the image content. This is a much easier learning task, but it also avoids the iterative process through which latent image priors are typically applied. Our approach directly estimates the motion flow from the blurred image through a fully-convolutional deep neural network (FCN) and recovers the unblurred image from the estimated motion flow. Our FCN is the first universal end-to-end mapping from the blurred image to the dense motion flow. To train the FCN, we simulate motion flows to generate synthetic blurred-image-motion-flow pairs thus avoiding the need for human labeling. Extensive experiments on challenging realistic blurred images demonstrate that the proposed method outperforms the state-of-the-art.