Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution

TL;DR

This paper introduces a Frequency-Transformer model for compressed video super-resolution that leverages joint space-time-frequency self-attention on spectral maps to effectively restore high-quality frames from degraded compressed videos.

Contribution

The novel Frequency-Transformer conducts fine-grained self-attention in the spectral domain, improving texture extraction and transfer in compressed video super-resolution tasks.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effective separation of textures from artifacts in spectral domain.

Divided attention scheme yields best enhancement results.

Abstract

Compressed video super-resolution (VSR) aims to restore high-resolution frames from compressed low-resolution counterparts. Most recent VSR approaches often enhance an input frame by borrowing relevant textures from neighboring video frames. Although some progress has been made, there are grand challenges to effectively extract and transfer high-quality textures from compressed videos where most frames are usually highly degraded. In this paper, we propose a novel Frequency-Transformer for compressed video super-resolution (FTVSR) that conducts self-attention over a joint space-time-frequency domain. First, we divide a video frame into patches, and transform each patch into DCT spectral maps in which each channel represents a frequency band. Such a design enables a fine-grained level self-attention on each frequency band, so that real visual texture can be distinguished from artifacts, and further utilized for video frame restoration. Second, we study different self-attention schemes, and discover that a divided attention which conducts a joint space-frequency attention before applying temporal attention on each frequency band, leads to the best video enhancement quality. Experimental results on two widely-used video super-resolution benchmarks show that FTVSR outperforms state-of-the-art approaches on both uncompressed and compressed videos with clear visual margins. Code is available at https://github.com/researchmm/FTVSR.