STDAN: Deformable Attention Network for Space-Time Video Super-Resolution

TL;DR

This paper introduces STDAN, a deformable attention network for space-time video super-resolution that leverages long-short term features and adaptive spatial-temporal aggregation to improve high-resolution video reconstruction.

Contribution

The paper proposes a novel STDAN model with LSTFI and STDFA modules, enhancing feature utilization and context aggregation for superior STVSR performance.

Findings

Outperforms state-of-the-art STVSR methods on multiple datasets.

Effectively exploits long-term neighboring frames for better interpolation.

Adaptive spatial-temporal aggregation improves high-resolution frame quality.

Abstract

The target of space-time video super-resolution (STVSR) is to increase the spatial-temporal resolution of low-resolution (LR) and low frame rate (LFR) videos. Recent approaches based on deep learning have made significant improvements, but most of them only use two adjacent frames, that is, short-term features, to synthesize the missing frame embedding, which cannot fully explore the information flow of consecutive input LR frames. In addition, existing STVSR models hardly exploit the temporal contexts explicitly to assist high-resolution (HR) frame reconstruction. To address these issues, in this paper, we propose a deformable attention network called STDAN for STVSR. First, we devise a long-short term feature interpolation (LSTFI) module, which is capable of excavating abundant content from more neighboring input frames for the interpolation process through a bidirectional RNN structure. Second, we put forward a spatial-temporal deformable feature aggregation (STDFA) module, in which spatial and temporal contexts in dynamic video frames are adaptively captured and aggregated to enhance SR reconstruction. Experimental results on several datasets demonstrate that our approach outperforms state-of-the-art STVSR methods. The code is available at https://github.com/littlewhitesea/STDAN.