Progressive Two-Stage Network for Low-Light Image Enhancement
At night, visual quality is reduced due to insufficient illumination so that it is difficult to conduct high-level visual tasks effectively. Existing image enhancement methods only focus on brightness improvement, however, improving image quality in low-light environments still remains a challenging...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/12/12/1458 |
| _version_ | 1797502476358778880 |
|---|---|
| author | Yanpeng Sun Zhanyou Chang Yong Zhao Zhengxu Hua Sirui Li |
| author_facet | Yanpeng Sun Zhanyou Chang Yong Zhao Zhengxu Hua Sirui Li |
| author_sort | Yanpeng Sun |
| collection | DOAJ |
| description | At night, visual quality is reduced due to insufficient illumination so that it is difficult to conduct high-level visual tasks effectively. Existing image enhancement methods only focus on brightness improvement, however, improving image quality in low-light environments still remains a challenging task. In order to overcome the limitations of existing enhancement algorithms with insufficient enhancement, a progressive two-stage image enhancement network is proposed in this paper. The low-light image enhancement problem is innovatively divided into two stages. The first stage of the network extracts the multi-scale features of the image through an encoder and decoder structure. The second stage of the network refines the results after enhancement to further improve output brightness. Experimental results and data analysis show that our method can achieve state-of-the-art performance on synthetic and real data sets, with both subjective and objective capability superior to other approaches. |
| first_indexed | 2024-03-10T03:33:38Z |
| format | Article |
| id | doaj.art-cffe5cf6fa4f416aa21753255a787908 |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-10T03:33:38Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-cffe5cf6fa4f416aa21753255a7879082023-11-23T09:35:37ZengMDPI AGMicromachines2072-666X2021-11-011212145810.3390/mi12121458Progressive Two-Stage Network for Low-Light Image EnhancementYanpeng Sun0Zhanyou Chang1Yong Zhao2Zhengxu Hua3Sirui Li4College of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang 110136, ChinaCollege of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang 110136, ChinaScience and Technology on Altitude Simulation Laboratory, Mianyan 621700, ChinaCollege of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang 110136, ChinaCollege of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang 110136, ChinaAt night, visual quality is reduced due to insufficient illumination so that it is difficult to conduct high-level visual tasks effectively. Existing image enhancement methods only focus on brightness improvement, however, improving image quality in low-light environments still remains a challenging task. In order to overcome the limitations of existing enhancement algorithms with insufficient enhancement, a progressive two-stage image enhancement network is proposed in this paper. The low-light image enhancement problem is innovatively divided into two stages. The first stage of the network extracts the multi-scale features of the image through an encoder and decoder structure. The second stage of the network refines the results after enhancement to further improve output brightness. Experimental results and data analysis show that our method can achieve state-of-the-art performance on synthetic and real data sets, with both subjective and objective capability superior to other approaches.https://www.mdpi.com/2072-666X/12/12/1458image enhancementtwo-stage networkresidual dense networkattentional mechanisms |
| spellingShingle | Yanpeng Sun Zhanyou Chang Yong Zhao Zhengxu Hua Sirui Li Progressive Two-Stage Network for Low-Light Image Enhancement Micromachines image enhancement two-stage network residual dense network attentional mechanisms |
| title | Progressive Two-Stage Network for Low-Light Image Enhancement |
| title_full | Progressive Two-Stage Network for Low-Light Image Enhancement |
| title_fullStr | Progressive Two-Stage Network for Low-Light Image Enhancement |
| title_full_unstemmed | Progressive Two-Stage Network for Low-Light Image Enhancement |
| title_short | Progressive Two-Stage Network for Low-Light Image Enhancement |
| title_sort | progressive two stage network for low light image enhancement |
| topic | image enhancement two-stage network residual dense network attentional mechanisms |
| url | https://www.mdpi.com/2072-666X/12/12/1458 |
| work_keys_str_mv | AT yanpengsun progressivetwostagenetworkforlowlightimageenhancement AT zhanyouchang progressivetwostagenetworkforlowlightimageenhancement AT yongzhao progressivetwostagenetworkforlowlightimageenhancement AT zhengxuhua progressivetwostagenetworkforlowlightimageenhancement AT siruili progressivetwostagenetworkforlowlightimageenhancement |