Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report

TL;DR

This paper presents the AIM 2022 Challenge focused on reversing the image signal processing pipeline to reconstruct raw sensor images from RGB images, aiming to advance low-level vision tasks and address dataset scarcity.

Contribution

It introduces a new challenge and benchmark for RAW reconstruction, establishing state-of-the-art methods for reversing ISP transformations without metadata.

Findings

Proposed methods outperform previous approaches in RAW reconstruction accuracy

Benchmark results set new standards for reversing ISP transformations

Generated RAW images improve performance in downstream tasks like denoising

Abstract

Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.