Saved in:
Bibliographic Details
Main Authors: Li, Baiang, Ma, Sizhuo, Zeng, Yanhong, Xu, Xiaogang, Fang, Youqing, Zhang, Zhao, Wang, Jian, Chen, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.09389
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916285861855232
author Li, Baiang
Ma, Sizhuo
Zeng, Yanhong
Xu, Xiaogang
Fang, Youqing
Zhang, Zhao
Wang, Jian
Chen, Kai
author_facet Li, Baiang
Ma, Sizhuo
Zeng, Yanhong
Xu, Xiaogang
Fang, Youqing
Zhang, Zhao
Wang, Jian
Chen, Kai
contents Capturing High Dynamic Range (HDR) scenery using 8-bit cameras often suffers from over-/underexposure, loss of fine details due to low bit-depth compression, skewed color distributions, and strong noise in dark areas. Traditional LDR image enhancement methods primarily focus on color mapping, which enhances the visual representation by expanding the image's color range and adjusting the brightness. However, these approaches fail to effectively restore content in dynamic range extremes, which are regions with pixel values close to 0 or 255. To address the full scope of challenges in HDR imaging and surpass the limitations of current models, we propose a novel two-stage approach. The first stage maps the color and brightness to an appropriate range while keeping the existing details, and the second stage utilizes a diffusion prior to generate content in dynamic range extremes lost during capture. This generative refinement module can also be used as a plug-and-play module to enhance and complement existing LDR enhancement models. The proposed method markedly improves the quality and details of LDR images, demonstrating superior performance through rigorous experimental validation. The project page is at https://sagiri0208.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2406_09389
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior
Li, Baiang
Ma, Sizhuo
Zeng, Yanhong
Xu, Xiaogang
Fang, Youqing
Zhang, Zhao
Wang, Jian
Chen, Kai
Image and Video Processing
Computer Vision and Pattern Recognition
Capturing High Dynamic Range (HDR) scenery using 8-bit cameras often suffers from over-/underexposure, loss of fine details due to low bit-depth compression, skewed color distributions, and strong noise in dark areas. Traditional LDR image enhancement methods primarily focus on color mapping, which enhances the visual representation by expanding the image's color range and adjusting the brightness. However, these approaches fail to effectively restore content in dynamic range extremes, which are regions with pixel values close to 0 or 255. To address the full scope of challenges in HDR imaging and surpass the limitations of current models, we propose a novel two-stage approach. The first stage maps the color and brightness to an appropriate range while keeping the existing details, and the second stage utilizes a diffusion prior to generate content in dynamic range extremes lost during capture. This generative refinement module can also be used as a plug-and-play module to enhance and complement existing LDR enhancement models. The proposed method markedly improves the quality and details of LDR images, demonstrating superior performance through rigorous experimental validation. The project page is at https://sagiri0208.github.io
title Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.09389