DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shin, UkCheol | ko |
dc.contributor.author | Lee, Kyung Hyun | ko |
dc.contributor.author | Kweon, In-So | ko |
dc.date.accessioned | 2023-08-31T09:01:04Z | - |
dc.date.available | 2023-08-31T09:01:04Z | - |
dc.date.created | 2023-02-24 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.citation | 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022, pp.7044 - 7051 | - |
dc.identifier.issn | 2153-0858 | - |
dc.identifier.uri | http://hdl.handle.net/10203/312076 | - |
dc.description.abstract | In this paper, we propose a multi-objective camera ISP framework that utilizes Deep Reinforcement Learning (DRL) and camera ISP toolbox that consist of network-based and conventional ISP tools. The proposed DRL-based camera ISP framework iteratively selects a proper tool from the toolbox and applies it to the image to maximize a given vision task-specific reward function. For this purpose, we implement total 51 ISP tools that include exposure correction, color-and-tone correction, white balance, sharpening, denoising, and the others. We also propose an efficient DRL network architecture that can extract the various aspects of an image and make a rigid mapping relationship between images and a large number of actions. Our proposed DRL-based ISP framework effectively improves the image quality according to each vision task such as RAW-to-RGB image restoration, 2D object detection, and monocular depth estimation. | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000909405300006 | - |
dc.identifier.scopusid | 2-s2.0-85146312210 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 7044 | - |
dc.citation.endingpage | 7051 | - |
dc.citation.publicationname | 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022 | - |
dc.identifier.conferencecountry | JA | - |
dc.identifier.conferencelocation | Kyoto | - |
dc.identifier.doi | 10.1109/IROS47612.2022.9981361 | - |
dc.contributor.localauthor | Kweon, In-So | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.