File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICIP42928.2021.9506201
- WOS: WOS:000819455103010
Supplementary
-
Citations:
- Web of Science: 0
- Appears in Collections:
Conference Paper: Ghost-Free HDR Imaging Via Unrolling Low-Rank Matrix Completion
Title | Ghost-Free HDR Imaging Via Unrolling Low-Rank Matrix Completion |
---|---|
Authors | |
Keywords | Image quality Deep learning Visualization Closed-form solutions Image synthesis |
Issue Date | 2021 |
Publisher | IEEE. |
Citation | 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, Alaska, USA, 19-22 September 2021. In 2021 IEEE International Conference on Image Processing (ICIP): proceedings, p. 2928-2932 How to Cite? |
Abstract | We propose a ghost-free high dynamic range (HDR) image synthesis algorithm by unrolling low-rank matrix completion. By exploiting the low-rank structure of the irradiance maps from low dynamic range (LDR) images, we formulate ghost-free HDR imaging as a general low-rank matrix completion problem. Then, we solve the problem iteratively using the augmented Lagrange multiplier (ALM) method. At each iteration, the optimization variables are updated by closed-form solutions and the regularizers are updated by learned deep neural networks. Experimental results show that the proposed algorithm provides better image qualities with fewer visual artifacts compared to state-of-the-art algorithms. |
Description | INSPEC Accession Number: 21731418 |
Persistent Identifier | http://hdl.handle.net/10722/314606 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Mai, T | - |
dc.contributor.author | Lam, EYM | - |
dc.contributor.author | Lee, C | - |
dc.date.accessioned | 2022-07-22T05:27:48Z | - |
dc.date.available | 2022-07-22T05:27:48Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, Alaska, USA, 19-22 September 2021. In 2021 IEEE International Conference on Image Processing (ICIP): proceedings, p. 2928-2932 | - |
dc.identifier.uri | http://hdl.handle.net/10722/314606 | - |
dc.description | INSPEC Accession Number: 21731418 | - |
dc.description.abstract | We propose a ghost-free high dynamic range (HDR) image synthesis algorithm by unrolling low-rank matrix completion. By exploiting the low-rank structure of the irradiance maps from low dynamic range (LDR) images, we formulate ghost-free HDR imaging as a general low-rank matrix completion problem. Then, we solve the problem iteratively using the augmented Lagrange multiplier (ALM) method. At each iteration, the optimization variables are updated by closed-form solutions and the regularizers are updated by learned deep neural networks. Experimental results show that the proposed algorithm provides better image qualities with fewer visual artifacts compared to state-of-the-art algorithms. | - |
dc.language | eng | - |
dc.publisher | IEEE. | - |
dc.relation.ispartof | 2021 IEEE International Conference on Image Processing (ICIP): proceedings | - |
dc.rights | 2021 IEEE International Conference on Image Processing (ICIP): proceedings. Copyright © IEEE. | - |
dc.subject | Image quality | - |
dc.subject | Deep learning | - |
dc.subject | Visualization | - |
dc.subject | Closed-form solutions | - |
dc.subject | Image synthesis | - |
dc.title | Ghost-Free HDR Imaging Via Unrolling Low-Rank Matrix Completion | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Lam, EYM: elam@eee.hku.hk | - |
dc.identifier.authority | Lam, EYM=rp00131 | - |
dc.identifier.doi | 10.1109/ICIP42928.2021.9506201 | - |
dc.identifier.hkuros | 334705 | - |
dc.identifier.spage | 2928 | - |
dc.identifier.epage | 2932 | - |
dc.identifier.isi | WOS:000819455103010 | - |
dc.publisher.place | United States | - |