MERIT: Multi-domain Efficient RAW Image Translation

TL;DR

MERIT is a unified multi-domain RAW image translation framework that effectively models sensor-specific noise and uses advanced attention mechanisms, enabling scalable translation across diverse camera sensors with improved quality.

Contribution

It introduces a single model for multi-domain RAW translation, sensor-aware noise modeling, and a new dataset for standardized evaluation, advancing scalability and performance.

Findings

Outperforms prior models in image quality by 5.56 dB

Reduces training iterations by 80%

Supports translation across five diverse camera sensors

Abstract

RAW images captured by different camera sensors exhibit substantial domain shifts due to varying spectral responses, noise characteristics, and tone behaviors, complicating their direct use in downstream computer vision tasks. Prior methods address this problem by training domain-specific RAW-to-RAW translators for each source-target pair, but such approaches do not scale to real-world scenarios involving multiple types of commercial cameras. In this work, we introduce MERIT, the first unified framework for multi-domain RAW image translation, which leverages a single model to perform translations across arbitrary camera domains. To address domain-specific noise discrepancies, we propose a sensor-aware noise modeling loss that explicitly aligns the signal-dependent noise statistics of the generated images with those of the target domain. We further enhance the generator with a conditional multi-scale large kernel attention module for improved context and sensor-aware feature modeling. To facilitate standardized evaluation, we introduce MDRAW, the first dataset tailored for multi-domain RAW image translation, comprising both paired and unpaired RAW captures from five diverse camera sensors across a wide range of scenes. Extensive experiments demonstrate that MERIT outperforms prior models in both quality (5.56 dB improvement) and scalability (80% reduction in training iterations).