# Human and Scene Motion Deblurring using Pseudo-blur Synthesizer

arXiv: https://arxiv.org/abs/2111.12911 · HTML: https://mlsanity.com/paper/2111.12911/

## Key facts

- Cited by 1 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 25 Nov 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [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)
- [Recasting Gradient-Based Meta-Learning as Hierarchical Bayes](https://mlsanity.com/paper/1801.08930/) (2018)
- [Human-Aware Motion Deblurring](https://mlsanity.com/paper/2001.06816/) (2020)
- [Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring](https://mlsanity.com/paper/2004.05343/) (2020)
- [Meta-Transfer Learning for Zero-Shot Super-Resolution](https://mlsanity.com/paper/2002.12213/) (2020)
- [Synthesizing Images of Humans in Unseen Poses](https://mlsanity.com/paper/1804.07739/) (2018)
- [Deep Semantic Face Deblurring](https://mlsanity.com/paper/1803.03345/) (2018)
- [Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm](https://mlsanity.com/paper/1710.11622/) (2017)
- [Fast Adaptation to Super-Resolution Networks via Meta-Learning](https://mlsanity.com/paper/2001.02905/) (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)
- [Scene-Adaptive Video Frame Interpolation via Meta-Learning](https://mlsanity.com/paper/2004.00779/) (2020)
- [Light Field Blind Motion Deblurring](https://mlsanity.com/paper/1704.05416/) (2017)
- [Stereo Video Deblurring](https://mlsanity.com/paper/1607.08421/) (2016)
- [Fast and Full-Resolution Light Field Deblurring using a Deep Neural Network](https://mlsanity.com/paper/1904.00352/) (2019)

## Built on by (most cited first, 1 of 1)

- [Human from Blur: Human Pose Tracking from Blurry Images](https://mlsanity.com/paper/2303.17209/) (2023)

## Abstract (arXiv)

Present-day deep learning-based motion deblurring methods utilize the pair of synthetic blur and sharp data to regress any particular framework. This task is designed for directly translating a blurry image input into its restored version as output. The aforementioned approach relies heavily on the quality of the synthetic blurry data, which are only available before the training stage. Handling this issue by providing a large amount of data is expensive for common usage. We answer this challenge by providing an on-the-fly blurry data augmenter that can be run during training and test stages. To fully utilize it, we incorporate an unorthodox scheme of deblurring framework that employs the sequence of blur-deblur-reblur-deblur steps. The reblur step is assisted by a reblurring module (synthesizer) that provides the reblurred version (pseudo-blur) of its sharp or deblurred counterpart. The proposed module is also equipped with hand-crafted prior extracted using the state-of-the-art human body statistical model. This prior is employed to map human and non-human regions during adversarial learning to fully perceive the characteristics of human-articulated and scene motion blurs. By engaging this approach, our deblurring module becomes adaptive and achieves superior outcomes compared to recent state-of-the-art deblurring algorithms.