# MERIT: Multi-domain Efficient RAW Image Translation

arXiv: https://arxiv.org/abs/2603.20836 · HTML: https://mlsanity.com/paper/2603.20836/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [Instance Segmentation in the Dark](https://mlsanity.com/paper/2304.14298/) (2023)
- [Towards Real Scene Super-Resolution with Raw Images](https://mlsanity.com/paper/1905.12156/) (2019)
- [UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation](https://mlsanity.com/paper/2203.02557/) (2022)
- [Human Pose Estimation in Extremely Low-Light Conditions](https://mlsanity.com/paper/2303.15410/) (2023)
- [Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis](https://mlsanity.com/paper/2406.06216/) (2024)
- [Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment](https://mlsanity.com/paper/2504.01503/) (2025)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images](https://mlsanity.com/paper/2408.14802/) (2024)
- [AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection](https://mlsanity.com/paper/2410.22939/) (2024)
- [Supervised and Unsupervised Learning of Parameterized Color Enhancement](https://mlsanity.com/paper/2001.05843/) (2019)
- [Semi-Supervised Raw-to-Raw Mapping](https://mlsanity.com/paper/2106.13883/) (2021)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)
- [Learning to See in the Extremely Dark](https://mlsanity.com/paper/2506.21132/) (2025)
- [Removing Reflections from RAW Photos](https://mlsanity.com/paper/2404.14414/) (2024)
- [Color Matching Using Hypernetwork-Based Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2503.11781/) (2025)

## Abstract (arXiv)

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).