# SATVSR: Scenario Adaptive Transformer for Cross Scenarios Video Super-Resolution

arXiv: https://arxiv.org/abs/2211.08703 · HTML: https://mlsanity.com/paper/2211.08703/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 16 Nov 2022.

## Builds on (most cited first, 9 of 9)

- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond](https://mlsanity.com/paper/2012.02181/) (2020)
- [TDAN: Temporally Deformable Alignment Network for Video Super-Resolution](https://mlsanity.com/paper/1812.02898/) (2018)
- [Frame-Recurrent Video Super-Resolution](https://mlsanity.com/paper/1801.04590/) (2018)
- [Video Super-Resolution Transformer](https://mlsanity.com/paper/2106.06847/) (2021)
- [Learning Trajectory-Aware Transformer for Video Super-Resolution](https://mlsanity.com/paper/2204.04216/) (2022)

## Abstract (arXiv)

Video Super-Resolution (VSR) aims to recover sequences of high-resolution (HR) frames from low-resolution (LR) frames. Previous methods mainly utilize temporally adjacent frames to assist the reconstruction of target frames. However, in the real world, there is a lot of irrelevant information in adjacent frames of videos with fast scene switching, these VSR methods cannot adaptively distinguish and select useful information. In contrast, with a transformer structure suitable for temporal tasks, we devise a novel adaptive scenario video super-resolution method. Specifically, we use optical flow to label the patches in each video frame, only calculate the attention of patches with the same label. Then select the most relevant label among them to supplement the spatial-temporal information of the target frame. This design can directly make the supplementary information come from the same scene as much as possible. We further propose a cross-scale feature aggregation module to better handle the scale variation problem. Compared with other video super-resolution methods, our method not only achieves significant performance gains on single-scene videos but also has better robustness on cross-scene datasets.