Pyramid Inter-Attention for High Dynamic Range Imaging
This paper proposes a novel approach to high-dynamic-range (HDR) imaging of dynamic scenes to eliminate ghosting artifacts in HDR images when in the presence of severe misalignment (large object or camera motion) in input low-dynamic-range (LDR) images. Recent non-flow-based methods suffer from ghos...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/18/5102 |
| _version_ | 1827706647350345728 |
|---|---|
| author | Sungil Choi Jaehoon Cho Wonil Song Jihwan Choe Jisung Yoo Kwanghoon Sohn |
| author_facet | Sungil Choi Jaehoon Cho Wonil Song Jihwan Choe Jisung Yoo Kwanghoon Sohn |
| author_sort | Sungil Choi |
| collection | DOAJ |
| description | This paper proposes a novel approach to high-dynamic-range (HDR) imaging of dynamic scenes to eliminate ghosting artifacts in HDR images when in the presence of severe misalignment (large object or camera motion) in input low-dynamic-range (LDR) images. Recent non-flow-based methods suffer from ghosting artifacts in the presence of large object motion. Flow-based methods face the same issue since their optical flow algorithms yield huge alignment errors. To eliminate ghosting artifacts, we propose a simple yet effective alignment network for solving the misalignment. The proposed pyramid inter-attention module (PIAM) performs alignment of LDR features by leveraging inter-attention maps. Additionally, to boost the representation of aligned features in the merging process, we propose a dual excitation block (DEB) that recalibrates each feature both spatially and channel-wise. Exhaustive experimental results demonstrate the effectiveness of the proposed PIAM and DEB, achieving state-of-the-art performance in terms of producing ghost-free HDR images. |
| first_indexed | 2024-03-10T16:30:32Z |
| format | Article |
| id | doaj.art-3f016c2600694f94b3752c70258bb04f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:30:32Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3f016c2600694f94b3752c70258bb04f2023-11-20T12:53:57ZengMDPI AGSensors1424-82202020-09-012018510210.3390/s20185102Pyramid Inter-Attention for High Dynamic Range ImagingSungil Choi0Jaehoon Cho1Wonil Song2Jihwan Choe3Jisung Yoo4Kwanghoon Sohn5Department of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaDepartment of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaDepartment of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaSamsung Electronics, Suwon 16677, KoreaSamsung Electronics, Suwon 16677, KoreaDepartment of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaThis paper proposes a novel approach to high-dynamic-range (HDR) imaging of dynamic scenes to eliminate ghosting artifacts in HDR images when in the presence of severe misalignment (large object or camera motion) in input low-dynamic-range (LDR) images. Recent non-flow-based methods suffer from ghosting artifacts in the presence of large object motion. Flow-based methods face the same issue since their optical flow algorithms yield huge alignment errors. To eliminate ghosting artifacts, we propose a simple yet effective alignment network for solving the misalignment. The proposed pyramid inter-attention module (PIAM) performs alignment of LDR features by leveraging inter-attention maps. Additionally, to boost the representation of aligned features in the merging process, we propose a dual excitation block (DEB) that recalibrates each feature both spatially and channel-wise. Exhaustive experimental results demonstrate the effectiveness of the proposed PIAM and DEB, achieving state-of-the-art performance in terms of producing ghost-free HDR images.https://www.mdpi.com/1424-8220/20/18/5102HDR imagingattention mechanismsoptical flow |
| spellingShingle | Sungil Choi Jaehoon Cho Wonil Song Jihwan Choe Jisung Yoo Kwanghoon Sohn Pyramid Inter-Attention for High Dynamic Range Imaging Sensors HDR imaging attention mechanisms optical flow |
| title | Pyramid Inter-Attention for High Dynamic Range Imaging |
| title_full | Pyramid Inter-Attention for High Dynamic Range Imaging |
| title_fullStr | Pyramid Inter-Attention for High Dynamic Range Imaging |
| title_full_unstemmed | Pyramid Inter-Attention for High Dynamic Range Imaging |
| title_short | Pyramid Inter-Attention for High Dynamic Range Imaging |
| title_sort | pyramid inter attention for high dynamic range imaging |
| topic | HDR imaging attention mechanisms optical flow |
| url | https://www.mdpi.com/1424-8220/20/18/5102 |
| work_keys_str_mv | AT sungilchoi pyramidinterattentionforhighdynamicrangeimaging AT jaehooncho pyramidinterattentionforhighdynamicrangeimaging AT wonilsong pyramidinterattentionforhighdynamicrangeimaging AT jihwanchoe pyramidinterattentionforhighdynamicrangeimaging AT jisungyoo pyramidinterattentionforhighdynamicrangeimaging AT kwanghoonsohn pyramidinterattentionforhighdynamicrangeimaging |