# Deformable Kernel Convolutional Network for Video Extreme Super-Resolution

arXiv: https://arxiv.org/abs/2010.00154 · HTML: https://mlsanity.com/paper/2010.00154/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

## Built on by (most cited first, 2 of 2)

- [Modeling Spatial Nonstationarity via Deformable Convolutions for Deep Traffic Flow Prediction](https://mlsanity.com/paper/2101.12010/) (2021)
- [SSD-Faster Net: A Hybrid Network for Industrial Defect Inspection](https://mlsanity.com/paper/2207.00589/) (2022)

## Abstract (arXiv)

Video super-resolution, which attempts to reconstruct high-resolution video frames from their corresponding low-resolution versions, has received increasingly more attention in recent years. Most existing approaches opt to use deformable convolution to temporally align neighboring frames and apply traditional spatial attention mechanism (convolution based) to enhance reconstructed features. However, such spatial-only strategies cannot fully utilize temporal dependency among video frames. In this paper, we propose a novel deep learning based VSR algorithm, named Deformable Kernel Spatial Attention Network (DKSAN). Thanks to newly designed Deformable Kernel Convolution Alignment (DKC_Align) and Deformable Kernel Spatial Attention (DKSA) modules, DKSAN can better exploit both spatial and temporal redundancies to facilitate the information propagation across different layers. We have tested DKSAN on AIM2020 Video Extreme Super-Resolution Challenge to super-resolve videos with a scale factor as large as 16. Experimental results demonstrate that our proposed DKSAN can achieve both better subjective and objective performance compared with the existing state-of-the-art EDVR on Vid3oC and IntVID datasets.