Saved in:
Bibliographic Details
Main Authors: Zhou, Xingyu, Long, Wei, Lu, Jingbo, Jiang, Shiyin, You, Weiyi, Wu, Haifeng, Gu, Shuhang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.02159
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912360841609216
author Zhou, Xingyu
Long, Wei
Lu, Jingbo
Jiang, Shiyin
You, Weiyi
Wu, Haifeng
Gu, Shuhang
author_facet Zhou, Xingyu
Long, Wei
Lu, Jingbo
Jiang, Shiyin
You, Weiyi
Wu, Haifeng
Gu, Shuhang
contents Video super-resolution (VSR) can achieve better performance compared to single image super-resolution by additionally leveraging temporal information. In particular, the recurrent-based VSR model exploits long-range temporal information during inference and achieves superior detail restoration. However, effectively learning these long-term dependencies within long videos remains a key challenge. To address this, we propose LRTI-VSR, a novel training framework for recurrent VSR that efficiently leverages Long-Range Refocused Temporal Information. Our framework includes a generic training strategy that utilizes temporal propagation features from long video clips while training on shorter video clips. Additionally, we introduce a refocused intra&inter-frame transformer block which allows the VSR model to selectively prioritize useful temporal information through its attention module while further improving inter-frame information utilization in the FFN module. We evaluate LRTI-VSR on both CNN and transformer-based VSR architectures, conducting extensive ablation studies to validate the contribution of each component. Experiments on long-video test sets demonstrate that LRTI-VSR achieves state-of-the-art performance while maintaining training and computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02159
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution
Zhou, Xingyu
Long, Wei
Lu, Jingbo
Jiang, Shiyin
You, Weiyi
Wu, Haifeng
Gu, Shuhang
Computer Vision and Pattern Recognition
Video super-resolution (VSR) can achieve better performance compared to single image super-resolution by additionally leveraging temporal information. In particular, the recurrent-based VSR model exploits long-range temporal information during inference and achieves superior detail restoration. However, effectively learning these long-term dependencies within long videos remains a key challenge. To address this, we propose LRTI-VSR, a novel training framework for recurrent VSR that efficiently leverages Long-Range Refocused Temporal Information. Our framework includes a generic training strategy that utilizes temporal propagation features from long video clips while training on shorter video clips. Additionally, we introduce a refocused intra&inter-frame transformer block which allows the VSR model to selectively prioritize useful temporal information through its attention module while further improving inter-frame information utilization in the FFN module. We evaluate LRTI-VSR on both CNN and transformer-based VSR architectures, conducting extensive ablation studies to validate the contribution of each component. Experiments on long-video test sets demonstrate that LRTI-VSR achieves state-of-the-art performance while maintaining training and computational efficiency.
title Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.02159