Interactive lighting editing system for single indoor low-light scene images with corresponding depth maps
We propose a novel interactive lighting editing system for lighting a single indoor RGB image based on spherical harmonic lighting. It allows users to intuitively edit illumination and relight the complicated low-light indoor scene. Our method not only achieves plausible global relighting but also e...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-12-01
|
Series: | Visual Informatics |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2468502X22000882 |
_version_ | 1798015816718876672 |
---|---|
author | Zhongyun Bao Gang Fu Lian Duan Chunxia Xiao |
author_facet | Zhongyun Bao Gang Fu Lian Duan Chunxia Xiao |
author_sort | Zhongyun Bao |
collection | DOAJ |
description | We propose a novel interactive lighting editing system for lighting a single indoor RGB image based on spherical harmonic lighting. It allows users to intuitively edit illumination and relight the complicated low-light indoor scene. Our method not only achieves plausible global relighting but also enhances the local details of the complicated scene according to the spatially-varying spherical harmonic lighting, which only requires a single RGB image along with a corresponding depth map. To this end, we first present a joint optimization algorithm, which is based on the geometric optimization of the depth map and intrinsic image decomposition avoiding texture-copy, for refining the depth map and obtaining the shading map. Then we propose a lighting estimation method based on spherical harmonic lighting, which not only achieves the global illumination estimation of the scene, but also further enhances local details of the complicated scene. Finally, we use a simple and intuitive interactive method to edit the environment lighting map to adjust lighting and relight the scene. Through extensive experimental results, we demonstrate that our proposed approach is simple and intuitive for relighting the low-light indoor scene, and achieve state-of-the-art results. |
first_indexed | 2024-04-11T15:40:49Z |
format | Article |
id | doaj.art-da84e50f678c474c98dd78001e3d4c4d |
institution | Directory Open Access Journal |
issn | 2468-502X |
language | English |
last_indexed | 2024-04-11T15:40:49Z |
publishDate | 2022-12-01 |
publisher | Elsevier |
record_format | Article |
series | Visual Informatics |
spelling | doaj.art-da84e50f678c474c98dd78001e3d4c4d2022-12-22T04:15:49ZengElsevierVisual Informatics2468-502X2022-12-01649099Interactive lighting editing system for single indoor low-light scene images with corresponding depth mapsZhongyun Bao0Gang Fu1Lian Duan2Chunxia Xiao3School of Computer Science, Wuhan University, Wuhan, 430072, Hubei, ChinaSchool of Computer Science, Wuhan University, Wuhan, 430072, Hubei, ChinaSchool of Computer Science, Wuhan University, Wuhan, 430072, Hubei, ChinaCorresponding author.; School of Computer Science, Wuhan University, Wuhan, 430072, Hubei, ChinaWe propose a novel interactive lighting editing system for lighting a single indoor RGB image based on spherical harmonic lighting. It allows users to intuitively edit illumination and relight the complicated low-light indoor scene. Our method not only achieves plausible global relighting but also enhances the local details of the complicated scene according to the spatially-varying spherical harmonic lighting, which only requires a single RGB image along with a corresponding depth map. To this end, we first present a joint optimization algorithm, which is based on the geometric optimization of the depth map and intrinsic image decomposition avoiding texture-copy, for refining the depth map and obtaining the shading map. Then we propose a lighting estimation method based on spherical harmonic lighting, which not only achieves the global illumination estimation of the scene, but also further enhances local details of the complicated scene. Finally, we use a simple and intuitive interactive method to edit the environment lighting map to adjust lighting and relight the scene. Through extensive experimental results, we demonstrate that our proposed approach is simple and intuitive for relighting the low-light indoor scene, and achieve state-of-the-art results.http://www.sciencedirect.com/science/article/pii/S2468502X22000882Image processingInteractive relightingSpherical harmonic lightingDepth mapIntrinsic image decomposition |
spellingShingle | Zhongyun Bao Gang Fu Lian Duan Chunxia Xiao Interactive lighting editing system for single indoor low-light scene images with corresponding depth maps Visual Informatics Image processing Interactive relighting Spherical harmonic lighting Depth map Intrinsic image decomposition |
title | Interactive lighting editing system for single indoor low-light scene images with corresponding depth maps |
title_full | Interactive lighting editing system for single indoor low-light scene images with corresponding depth maps |
title_fullStr | Interactive lighting editing system for single indoor low-light scene images with corresponding depth maps |
title_full_unstemmed | Interactive lighting editing system for single indoor low-light scene images with corresponding depth maps |
title_short | Interactive lighting editing system for single indoor low-light scene images with corresponding depth maps |
title_sort | interactive lighting editing system for single indoor low light scene images with corresponding depth maps |
topic | Image processing Interactive relighting Spherical harmonic lighting Depth map Intrinsic image decomposition |
url | http://www.sciencedirect.com/science/article/pii/S2468502X22000882 |
work_keys_str_mv | AT zhongyunbao interactivelightingeditingsystemforsingleindoorlowlightsceneimageswithcorrespondingdepthmaps AT gangfu interactivelightingeditingsystemforsingleindoorlowlightsceneimageswithcorrespondingdepthmaps AT lianduan interactivelightingeditingsystemforsingleindoorlowlightsceneimageswithcorrespondingdepthmaps AT chunxiaxiao interactivelightingeditingsystemforsingleindoorlowlightsceneimageswithcorrespondingdepthmaps |