RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report

TL;DR

This paper reports on the NTIRE 2025 challenge where over 150 teams developed models to reconstruct RAW sensor images from sRGB images on smartphones, advancing the state-of-the-art in reverse ISP tasks.

Contribution

It introduces a large-scale challenge with new benchmark data for RAW reconstruction from sRGB images, fostering progress in this underexplored area.

Findings

Established new state-of-the-art models for RAW reconstruction

Demonstrated the effectiveness of challenge-based benchmarking

Provided insights into model efficiency and accuracy trade-offs

Abstract

Numerous low-level vision tasks operate in the RAW domain due to its linear properties, bit depth, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public sRGB datasets. For this reason, many approaches try to generate realistic RAW images using sensor information and sRGB images. This paper covers the second challenge on RAW Reconstruction from sRGB (Reverse ISP). We aim to recover RAW sensor images from smartphones given the corresponding sRGB images without metadata and, by doing this, ``reverse" the ISP transformation. Over 150 participants joined this NTIRE 2025 challenge and submitted efficient models. The proposed methods and benchmark establish the state-of-the-art for generating realistic RAW data.