RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution

TL;DR

This paper introduces RBSR, a recurrent network for burst super-resolution that effectively fuses information from multiple low-resolution images to produce high-resolution outputs, emphasizing the role of a base frame and an implicit weighting loss.

Contribution

It proposes a novel recurrent network architecture that uses a base frame as a prompt and an implicit weighting loss to enhance burst super-resolution performance.

Findings

Outperforms state-of-the-art methods on synthetic datasets

Effective in real-world burst super-resolution scenarios

Flexible in handling variable input frame numbers

Abstract

Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images, which is conducive to enhancing the imaging effects of smartphones with limited sensors. The main challenge of BurstSR is to effectively combine the complementary information from input frames, while existing methods still struggle with it. In this paper, we suggest fusing cues frame-by-frame with an efficient and flexible recurrent network. In particular, we emphasize the role of the base-frame and utilize it as a key prompt to guide the knowledge acquisition from other frames in every recurrence. Moreover, we introduce an implicit weighting loss to improve the model's flexibility in facing input frames with variable numbers. Extensive experiments on both synthetic and real-world datasets demonstrate that our method achieves better results than state-of-the-art ones. Codes and pre-trained models are available at https://github.com/ZcsrenlongZ/RBSR.