# Deep Video Deblurring: The Devil is in the Details

arXiv: https://arxiv.org/abs/1909.12196 · HTML: https://mlsanity.com/paper/1909.12196/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2019.

## Built on by (most cited first, 4 of 4)

- [Flow-Guided Sparse Transformer for Video Deblurring](https://mlsanity.com/paper/2201.01893/) (2022)
- [Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes](https://mlsanity.com/paper/2108.09982/) (2021)
- [Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring](https://mlsanity.com/paper/2112.05150/) (2021)
- [Multi-Scale Memory-Based Video Deblurring](https://mlsanity.com/paper/2204.02977/) (2022)

## Abstract (arXiv)

Video deblurring for hand-held cameras is a challenging task, since the underlying blur is caused by both camera shake and object motion. State-of-the-art deep networks exploit temporal information from neighboring frames, either by means of spatio-temporal transformers or by recurrent architectures. In contrast to these involved models, we found that a simple baseline CNN can perform astonishingly well when particular care is taken w.r.t. the details of model and training procedure. To that end, we conduct a comprehensive study regarding these crucial details, uncovering extreme differences in quantitative and qualitative performance. Exploiting these details allows us to boost the architecture and training procedure of a simple baseline CNN by a staggering 3.15dB, such that it becomes highly competitive w.r.t. cutting-edge networks. This raises the question whether the reported accuracy difference between models is always due to technical contributions or also subject to such orthogonal, but crucial details.