Feature separation and non-shadow information-guided shadow removal network
To tackle the performance bottlenecks and color deviation issues stemming from current shadow removal methods, a feature separation and non-shadow information guided shadow removal network (FSNIG-ShadowNet) was constructed. In the separation and reconstruction stage, the shadow image was separated i...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2024-05-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024099/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539173872304128 |
|---|---|
| author | HUANG Ying FANG Shaojie CHENG Bin JIANG Mao QIAN Ying |
| author_facet | HUANG Ying FANG Shaojie CHENG Bin JIANG Mao QIAN Ying |
| author_sort | HUANG Ying |
| collection | DOAJ |
| description | To tackle the performance bottlenecks and color deviation issues stemming from current shadow removal methods, a feature separation and non-shadow information guided shadow removal network (FSNIG-ShadowNet) was constructed. In the separation and reconstruction stage, the shadow image was separated into direct light and ambient light using self-reconstruction supervision, with decoupling of lighting types and reflectance. Subsequently, a decoder was employed to re-couple the separated features to yield shadow-free images. In the refinement stage, the network focused on the adjacent regions of shadow and non-shadow, incorporating a local region adaptive normalization module to transfer the color priors of local non-shadow region to shadow regions for mitigating color deviation between the two regions. Experimental results demonstrate that the proposed FSNIG-ShadowNet achieves competitive results compared to other state-of-the-art methods. |
| format | Article |
| id | doaj-art-16f2ecfc90d444d1893b134656548080 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2024-05-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-16f2ecfc90d444d1893b1346565480802025-01-14T07:24:26ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2024-05-014517819062276831Feature separation and non-shadow information-guided shadow removal networkHUANG YingFANG ShaojieCHENG BinJIANG MaoQIAN YingTo tackle the performance bottlenecks and color deviation issues stemming from current shadow removal methods, a feature separation and non-shadow information guided shadow removal network (FSNIG-ShadowNet) was constructed. In the separation and reconstruction stage, the shadow image was separated into direct light and ambient light using self-reconstruction supervision, with decoupling of lighting types and reflectance. Subsequently, a decoder was employed to re-couple the separated features to yield shadow-free images. In the refinement stage, the network focused on the adjacent regions of shadow and non-shadow, incorporating a local region adaptive normalization module to transfer the color priors of local non-shadow region to shadow regions for mitigating color deviation between the two regions. Experimental results demonstrate that the proposed FSNIG-ShadowNet achieves competitive results compared to other state-of-the-art methods.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024099/shadow removalfeature separationself-reconstructioncolor prior |
| spellingShingle | HUANG Ying FANG Shaojie CHENG Bin JIANG Mao QIAN Ying Feature separation and non-shadow information-guided shadow removal network Tongxin xuebao shadow removal feature separation self-reconstruction color prior |
| title | Feature separation and non-shadow information-guided shadow removal network |
| title_full | Feature separation and non-shadow information-guided shadow removal network |
| title_fullStr | Feature separation and non-shadow information-guided shadow removal network |
| title_full_unstemmed | Feature separation and non-shadow information-guided shadow removal network |
| title_short | Feature separation and non-shadow information-guided shadow removal network |
| title_sort | feature separation and non shadow information guided shadow removal network |
| topic | shadow removal feature separation self-reconstruction color prior |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024099/ |
| work_keys_str_mv | AT huangying featureseparationandnonshadowinformationguidedshadowremovalnetwork AT fangshaojie featureseparationandnonshadowinformationguidedshadowremovalnetwork AT chengbin featureseparationandnonshadowinformationguidedshadowremovalnetwork AT jiangmao featureseparationandnonshadowinformationguidedshadowremovalnetwork AT qianying featureseparationandnonshadowinformationguidedshadowremovalnetwork |