A high dynamic range imaging method for short exposure multiview images
The restoration and enhancement of multiview low dynamic range (MVLDR) images captured in low lighting conditions is a great challenge. The disparity maps are hardly reliable in practical, real-world scenarios and suffers from holes and artifacts due to large baseline and angle deviation among multi...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/172039 |
| _version_ | 1811694712334057472 |
|---|---|
| author | Khan, Rizwan Yang, You Wu, Kejun Mehmood, Atif Qaisar, Zahid Hussain Zheng, Zhonglong |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Khan, Rizwan Yang, You Wu, Kejun Mehmood, Atif Qaisar, Zahid Hussain Zheng, Zhonglong |
| author_sort | Khan, Rizwan |
| collection | NTU |
| description | The restoration and enhancement of multiview low dynamic range (MVLDR) images captured in low lighting conditions is a great challenge. The disparity maps are hardly reliable in practical, real-world scenarios and suffers from holes and artifacts due to large baseline and angle deviation among multiple cameras in low lighting conditions. Furthermore, multiple images with some additional information (e.g., ISO/exposure time, etc.) are required for the radiance map and poses the additional challenges of deghosting to encounter motion artifacts. In this paper, we proposed a method to reconstruct multiview high dynamic range (MVHDR) images from MVLDR images without relying on disparity maps. We detect and accurately match the feature points among the involved input views and gather the brightness information from the neighboring viewpoints to optimize an image restoration function based on input exposure gain to finally generate MVHDR images. Our method is very reliable and suitable for a wide baseline among sparse cameras. The proposed method requires only one image per viewpoint without any additional information and outperforms others. |
| first_indexed | 2024-10-01T07:11:56Z |
| format | Journal Article |
| id | ntu-10356/172039 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:11:56Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1720392023-11-20T04:46:35Z A high dynamic range imaging method for short exposure multiview images Khan, Rizwan Yang, You Wu, Kejun Mehmood, Atif Qaisar, Zahid Hussain Zheng, Zhonglong School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Multiview Camera Image Enhancement The restoration and enhancement of multiview low dynamic range (MVLDR) images captured in low lighting conditions is a great challenge. The disparity maps are hardly reliable in practical, real-world scenarios and suffers from holes and artifacts due to large baseline and angle deviation among multiple cameras in low lighting conditions. Furthermore, multiple images with some additional information (e.g., ISO/exposure time, etc.) are required for the radiance map and poses the additional challenges of deghosting to encounter motion artifacts. In this paper, we proposed a method to reconstruct multiview high dynamic range (MVHDR) images from MVLDR images without relying on disparity maps. We detect and accurately match the feature points among the involved input views and gather the brightness information from the neighboring viewpoints to optimize an image restoration function based on input exposure gain to finally generate MVHDR images. Our method is very reliable and suitable for a wide baseline among sparse cameras. The proposed method requires only one image per viewpoint without any additional information and outperforms others. This work was funded by the National Natural Science Foundation of China NSFC62272419, U22A20102, Natural Science Foundation of Zhejiang Province ZJNSFLZ22F020010 and Zhejiang Normal University Research Fund ZC304022915. 2023-11-20T04:46:35Z 2023-11-20T04:46:35Z 2023 Journal Article Khan, R., Yang, Y., Wu, K., Mehmood, A., Qaisar, Z. H. & Zheng, Z. (2023). A high dynamic range imaging method for short exposure multiview images. Pattern Recognition, 137, 109344-. https://dx.doi.org/10.1016/j.patcog.2023.109344 0031-3203 https://hdl.handle.net/10356/172039 10.1016/j.patcog.2023.109344 2-s2.0-85146632665 137 109344 en Pattern Recognition © 2023 Elsevier Ltd. All rights reserved. |
| spellingShingle | Engineering::Electrical and electronic engineering Multiview Camera Image Enhancement Khan, Rizwan Yang, You Wu, Kejun Mehmood, Atif Qaisar, Zahid Hussain Zheng, Zhonglong A high dynamic range imaging method for short exposure multiview images |
| title | A high dynamic range imaging method for short exposure multiview images |
| title_full | A high dynamic range imaging method for short exposure multiview images |
| title_fullStr | A high dynamic range imaging method for short exposure multiview images |
| title_full_unstemmed | A high dynamic range imaging method for short exposure multiview images |
| title_short | A high dynamic range imaging method for short exposure multiview images |
| title_sort | high dynamic range imaging method for short exposure multiview images |
| topic | Engineering::Electrical and electronic engineering Multiview Camera Image Enhancement |
| url | https://hdl.handle.net/10356/172039 |
| work_keys_str_mv | AT khanrizwan ahighdynamicrangeimagingmethodforshortexposuremultiviewimages AT yangyou ahighdynamicrangeimagingmethodforshortexposuremultiviewimages AT wukejun ahighdynamicrangeimagingmethodforshortexposuremultiviewimages AT mehmoodatif ahighdynamicrangeimagingmethodforshortexposuremultiviewimages AT qaisarzahidhussain ahighdynamicrangeimagingmethodforshortexposuremultiviewimages AT zhengzhonglong ahighdynamicrangeimagingmethodforshortexposuremultiviewimages AT khanrizwan highdynamicrangeimagingmethodforshortexposuremultiviewimages AT yangyou highdynamicrangeimagingmethodforshortexposuremultiviewimages AT wukejun highdynamicrangeimagingmethodforshortexposuremultiviewimages AT mehmoodatif highdynamicrangeimagingmethodforshortexposuremultiviewimages AT qaisarzahidhussain highdynamicrangeimagingmethodforshortexposuremultiviewimages AT zhengzhonglong highdynamicrangeimagingmethodforshortexposuremultiviewimages |