# Deblurring using Analysis-Synthesis Networks Pair

arXiv: https://arxiv.org/abs/2004.02956 · HTML: https://mlsanity.com/paper/2004.02956/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 29 of 29)

- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [MC-Blur: A Comprehensive Benchmark for Image Deblurring](https://mlsanity.com/paper/2112.00234/) (2021)
- [Face Deblurring using Dual Camera Fusion on Mobile Phones](https://mlsanity.com/paper/2207.11617/) (2022)
- [End-to-end Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2105.06878/) (2021)
- [Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos](https://mlsanity.com/paper/2111.14465/) (2021)
- [Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networks](https://mlsanity.com/paper/2308.02947/) (2023)
- [End-to-end Alternating Optimization for Real-World Blind Super Resolution](https://mlsanity.com/paper/2308.08816/) (2023)
- [Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding](https://mlsanity.com/paper/2105.13077/) (2021)
- [Posterior Sampling for Image Restoration using Explicit Patch Priors](https://mlsanity.com/paper/2104.09895/) (2021)
- [Deep learning in motion deblurring: current status, benchmarks and future prospects](https://mlsanity.com/paper/2401.05055/) (2024)
- [Learning to Deblur Polarized Images](https://mlsanity.com/paper/2402.18134/) (2024)
- [Deep Idempotent Network for Efficient Single Image Blind Deblurring](https://mlsanity.com/paper/2210.07122/) (2022)
- [Neural Image Re-Exposure](https://mlsanity.com/paper/2305.13593/) (2023)
- [A Deep Variational Bayesian Framework for Blind Image Deblurring](https://mlsanity.com/paper/2106.02884/) (2021)
- [Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency](https://mlsanity.com/paper/2106.14336/) (2021)
- [LODE: Deep Local Deblurring and A New Benchmark](https://mlsanity.com/paper/2109.09149/) (2021)
- [Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring](https://mlsanity.com/paper/2204.12139/) (2022)
- [Human from Blur: Human Pose Tracking from Blurry Images](https://mlsanity.com/paper/2303.17209/) (2023)
- [Deep Hybrid Camera Deblurring for Smartphone Cameras](https://mlsanity.com/paper/2312.13317/) (2023)
- [Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding](https://mlsanity.com/paper/2407.14816/) (2024)
- [Non-uniform Motion Deblurring with Blurry Component Divided Guidance](https://mlsanity.com/paper/2101.06021/) (2021)
- [Wiener Guided DIP for Unsupervised Blind Image Deconvolution](https://mlsanity.com/paper/2112.10271/) (2021)
- [Towards Real-World Video Deblurring by Exploring Blur Formation Process](https://mlsanity.com/paper/2208.13184/) (2022)
- [Image Motion Blur Removal in the Temporal Dimension with Video Diffusion Models](https://mlsanity.com/paper/2501.12604/) (2025)
- [Blur2seq: Blind Deblurring and Camera Trajectory Estimation from a Single Camera Motion-blurred Image](https://mlsanity.com/paper/2510.20539/) (2025)
- [Assessing the Role of Datasets in the Generalization of Motion Deblurring Methods to Real Images](https://mlsanity.com/paper/2209.12675/) (2022)
- [Evaluation of neural network algorithms for atmospheric turbulence mitigation](https://mlsanity.com/paper/2410.20816/) (2024)
- [Frequency-domain Learning with Kernel Prior for Blind Image Deblurring](https://mlsanity.com/paper/2504.14664/) (2025)
- [Generative Latent Kernel Modeling for Blind Motion Deblurring](https://mlsanity.com/paper/2507.09285/) (2025)

## Abstract (arXiv)

Blind image deblurring remains a challenging problem for modern artificial neural networks. Unlike other image restoration problems, deblurring networks fail behind the performance of existing deblurring algorithms in case of uniform and 3D blur models. This follows from the diverse and profound effect that the unknown blur-kernel has on the deblurring operator. We propose a new architecture which breaks the deblurring network into an analysis network which estimates the blur, and a synthesis network that uses this kernel to deblur the image. Unlike existing deblurring networks, this design allows us to explicitly incorporate the blur-kernel in the network's training. In addition, we introduce new cross-correlation layers that allow better blur estimations, as well as unique components that allow the estimate blur to control the action of the synthesis deblurring action. Evaluating the new approach over established benchmark datasets shows its ability to achieve state-of-the-art deblurring accuracy on various tests, as well as offer a major speedup in runtime.