Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey

This paper reviews the NTIRE 2024 RAW Image Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. Th goal of this challenge is to upscale RAW Bayer images by 2x, considering unknown degradations such as noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. The performance of the top-5 sub-missions is reviewed and provided here as a gauge for the current state-of-the-art in RAW Image Super-Resolution.

1. Introduction

RAW Image Super-Resolution represents an active research direction, aiming at upscaling hardware-specific RAW image representations, while dealing with hardware characteristic properties, often depending on the technical implementation of the camera product. The lack of standardization in camera Image Processing Signal (ISP) implementation induces plenty variety into the camera market segment, with plenty corrections made through image processing algorithms [17], [18], [24], [25], [53], overcoming the hardware limitations of various devices.