MERIT: Multi-domain Efficient RAW Image Translation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918401243348992 |
|---|---|
| author | Huang, Wenjun Fu, Shenghao Jin, Yian Ni, Yang Cui, Ziteng Chen, Hanning He, Yirui Liu, Yezi Yun, Sanggeon Jeong, SungHeon Masukawa, Ryozo Chung, William Youngwoo Imani, Mohsen |
| author_facet | Huang, Wenjun Fu, Shenghao Jin, Yian Ni, Yang Cui, Ziteng Chen, Hanning He, Yirui Liu, Yezi Yun, Sanggeon Jeong, SungHeon Masukawa, Ryozo Chung, William Youngwoo Imani, Mohsen |
| contents | 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20836 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MERIT: Multi-domain Efficient RAW Image Translation Huang, Wenjun Fu, Shenghao Jin, Yian Ni, Yang Cui, Ziteng Chen, Hanning He, Yirui Liu, Yezi Yun, Sanggeon Jeong, SungHeon Masukawa, Ryozo Chung, William Youngwoo Imani, Mohsen Computer Vision and Pattern Recognition Artificial Intelligence 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). |
| title | MERIT: Multi-domain Efficient RAW Image Translation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.20836 |