Video Super-resolution with Temporal Group Attention
This work addresses the problem of enhancing video resolution for applications like streaming or surveillance, but it appears incremental as it builds on existing temporal integration techniques.
The paper tackles video super-resolution by proposing a method that hierarchically incorporates temporal information through grouping frames by frame rate, using attention and fusion modules, and handling large motion with fast spatial alignment, achieving favorable performance against state-of-the-art methods on benchmark datasets.
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention. In this work, we propose a novel method that can effectively incorporate temporal information in a hierarchical way. The input sequence is divided into several groups, with each one corresponding to a kind of frame rate. These groups provide complementary information to recover missing details in the reference frame, which is further integrated with an attention module and a deep intra-group fusion module. In addition, a fast spatial alignment is proposed to handle videos with large motion. Extensive results demonstrate the capability of the proposed model in handling videos with various motion. It achieves favorable performance against state-of-the-art methods on several benchmark datasets.