File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR42600.2020.00189
- Scopus: eid_2-s2.0-85094634358
- WOS: WOS:000620679502008
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Learning a Reinforced Agent for Flexible Exposure Bracketing Selection
Title | Learning a Reinforced Agent for Flexible Exposure Bracketing Selection |
---|---|
Authors | |
Keywords | Semantics Dynamic range Feature extraction Learning (artificial intelligence) Cameras |
Issue Date | 2020 |
Publisher | IEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147 |
Citation | Proceedings of IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, USA, 14-19 June 2020, p. 1817-1825 How to Cite? |
Abstract | Automatically selecting exposure bracketing (images exposed differently) is important to obtain a high dynamic range image by using multi-exposure fusion. Unlike previous methods that have many restrictions such as requiring camera response function, sensor noise model, and a stream of preview images with different exposures (not accessible in some scenarios e.g. mobile applications), we propose a novel deep neural network to automatically select exposure bracketing, named EBSNet, which is sufficiently flexible without having the above restrictions. EBSNet is formulated as a reinforced agent that is trained by maximizing rewards provided by a multi-exposure fusion network (MEFNet). By utilizing the illumination and semantic information extracted from just a single auto-exposure preview image, EBSNet enables to select an optimal exposure bracketing for multi-exposure fusion. EBSNet and MEFNet can be jointly trained to produce favorable results against recent state-of-the-art approaches. To facilitate future research, we provide a new benchmark dataset for multi-exposure selection and fusion. |
Description | Session: Poster 1.2 — 3D From Multiview and Sensors; Computational Photography; Efficient Training and Inference Methods for Networks - Poster no. 57 ; Paper ID 1804 CVPR 2020 held virtually due to COVID-19 |
Persistent Identifier | http://hdl.handle.net/10722/284165 |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, Z | - |
dc.contributor.author | Zhang, J | - |
dc.contributor.author | Lin, M | - |
dc.contributor.author | Wang, J | - |
dc.contributor.author | Luo, P | - |
dc.contributor.author | Ren, J | - |
dc.date.accessioned | 2020-07-20T05:56:36Z | - |
dc.date.available | 2020-07-20T05:56:36Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Proceedings of IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, USA, 14-19 June 2020, p. 1817-1825 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10722/284165 | - |
dc.description | Session: Poster 1.2 — 3D From Multiview and Sensors; Computational Photography; Efficient Training and Inference Methods for Networks - Poster no. 57 ; Paper ID 1804 | - |
dc.description | CVPR 2020 held virtually due to COVID-19 | - |
dc.description.abstract | Automatically selecting exposure bracketing (images exposed differently) is important to obtain a high dynamic range image by using multi-exposure fusion. Unlike previous methods that have many restrictions such as requiring camera response function, sensor noise model, and a stream of preview images with different exposures (not accessible in some scenarios e.g. mobile applications), we propose a novel deep neural network to automatically select exposure bracketing, named EBSNet, which is sufficiently flexible without having the above restrictions. EBSNet is formulated as a reinforced agent that is trained by maximizing rewards provided by a multi-exposure fusion network (MEFNet). By utilizing the illumination and semantic information extracted from just a single auto-exposure preview image, EBSNet enables to select an optimal exposure bracketing for multi-exposure fusion. EBSNet and MEFNet can be jointly trained to produce favorable results against recent state-of-the-art approaches. To facilitate future research, we provide a new benchmark dataset for multi-exposure selection and fusion. | - |
dc.language | eng | - |
dc.publisher | IEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147 | - |
dc.relation.ispartof | IEEE Conference on Computer Vision and Pattern Recognition. Proceedings | - |
dc.rights | IEEE Conference on Computer Vision and Pattern Recognition. Proceedings. Copyright © IEEE Computer Society. | - |
dc.rights | ©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.subject | Semantics | - |
dc.subject | Dynamic range | - |
dc.subject | Feature extraction | - |
dc.subject | Learning (artificial intelligence) | - |
dc.subject | Cameras | - |
dc.title | Learning a Reinforced Agent for Flexible Exposure Bracketing Selection | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR42600.2020.00189 | - |
dc.identifier.scopus | eid_2-s2.0-85094634358 | - |
dc.identifier.hkuros | 311026 | - |
dc.identifier.spage | 1817 | - |
dc.identifier.epage | 1825 | - |
dc.identifier.isi | WOS:000620679502008 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1063-6919 | - |