ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Berdan, Radu, Besbinar, Beril, Reinders, Christoph, Otsuka, Junji, Iso, Daisuke
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915183277899776
author Berdan, Radu
Besbinar, Beril
Reinders, Christoph
Otsuka, Junji
Iso, Daisuke
author_facet Berdan, Radu
Besbinar, Beril
Reinders, Christoph
Otsuka, Junji
Iso, Daisuke
contents Edge-based computer vision models running on compact, resource-limited devices benefit greatly from using unprocessed, detail-rich RAW sensor data instead of processed RGB images. Training these models, however, necessitates large labeled RAW datasets, which are costly and often impractical to obtain. Thus, converting existing labeled RGB datasets into sensor-specific RAW images becomes crucial for effective model training. In this paper, we introduce ReRAW, an RGB-to-RAW conversion model that achieves state-of-the-art reconstruction performance across five diverse RAW datasets. This is accomplished through ReRAW's novel multi-head architecture predicting RAW image candidates in gamma space. The performance is further boosted by a stratified sampling-based training data selection heuristic, which helps the model better reconstruct brighter RAW pixels. We finally demonstrate that pretraining compact models on a combination of high-quality synthetic RAW datasets (such as generated by ReRAW) and ground-truth RAW images for downstream tasks like object detection, outperforms both standard RGB pipelines, and RAW fine-tuning of RGB-pretrained models for the same task.
format Preprint
id arxiv_https___arxiv_org_abs_2503_03782
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge
Berdan, Radu
Besbinar, Beril
Reinders, Christoph
Otsuka, Junji
Iso, Daisuke
Image and Video Processing
Edge-based computer vision models running on compact, resource-limited devices benefit greatly from using unprocessed, detail-rich RAW sensor data instead of processed RGB images. Training these models, however, necessitates large labeled RAW datasets, which are costly and often impractical to obtain. Thus, converting existing labeled RGB datasets into sensor-specific RAW images becomes crucial for effective model training. In this paper, we introduce ReRAW, an RGB-to-RAW conversion model that achieves state-of-the-art reconstruction performance across five diverse RAW datasets. This is accomplished through ReRAW's novel multi-head architecture predicting RAW image candidates in gamma space. The performance is further boosted by a stratified sampling-based training data selection heuristic, which helps the model better reconstruct brighter RAW pixels. We finally demonstrate that pretraining compact models on a combination of high-quality synthetic RAW datasets (such as generated by ReRAW) and ground-truth RAW images for downstream tasks like object detection, outperforms both standard RGB pipelines, and RAW fine-tuning of RGB-pretrained models for the same task.
title ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge
topic Image and Video Processing
url https://arxiv.org/abs/2503.03782