NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results

TL;DR

This paper reviews the NTIRE2021 challenge on burst super-resolution, highlighting diverse methods that achieved state-of-the-art results in generating high-resolution images from noisy bursts.

Contribution

It presents a comprehensive overview of challenge methods and results, establishing new benchmarks for burst super-resolution performance.

Findings

Top methods set new state-of-the-art performance.

Diverse solutions effectively enhanced image resolution.

Real-world and synthetic data were both used for evaluation.

Abstract

This paper reviews the NTIRE2021 challenge on burst super-resolution. Given a RAW noisy burst as input, the task in the challenge was to generate a clean RGB image with 4 times higher resolution. The challenge contained two tracks; Track 1 evaluating on synthetically generated data, and Track 2 using real-world bursts from mobile camera. In the final testing phase, 6 teams submitted results using a diverse set of solutions. The top-performing methods set a new state-of-the-art for the burst super-resolution task.