DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Jinwoo | ko |
dc.contributor.author | Park, Hunmin | ko |
dc.contributor.author | Yoon, Sung-Eui | ko |
dc.contributor.author | Woo, Woontack | ko |
dc.date.accessioned | 2020-04-21T07:20:16Z | - |
dc.date.available | 2020-04-21T07:20:16Z | - |
dc.date.created | 2020-03-18 | - |
dc.date.created | 2020-03-18 | - |
dc.date.issued | 2020-03 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, v.26, no.5, pp.2002 - 2011 | - |
dc.identifier.issn | 1077-2626 | - |
dc.identifier.uri | http://hdl.handle.net/10203/273944 | - |
dc.description.abstract | In mixed reality (MR), augmenting virtual objects consistently with real-world illumination is one of the key factors that provide a realistic and immersive user experience. For this purpose, we propose a novel deep learning-based method to estimate high dynamic range (HDR) illumination from a single RGB image of a reference object. To obtain illumination of a current scene, previous approaches inserted a special camera in that scene, which may interfere with user's immersion, or they analyzed reflected radiances from a passive light probe with a specific type of materials or a known shape. The proposed method does not require any additional gadgets or strong prior cues, and aims to predict illumination from a single image of an observed object with a wide range of homogeneous materials and shapes. To effectively solve this ill-posed inverse rendering problem, three sequential deep neural networks are employed based on a physically-inspired design. These networks perform end-to-end regression to gradually decrease dependency on the material and shape. To cover various conditions, the proposed networks are trained on a large synthetic dataset generated by physically-based rendering. Finally, the reconstructed HDR illumination enables realistic image-based lighting of virtual objects in MR. Experimental results demonstrate the effectiveness of this approach compared against state-of-the-art methods. The paper also suggests some interesting MR applications in indoor and outdoor scenes. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | Physically-inspired Deep Light Estimation from a Homogeneous-Material Object for Mixed Reality Lighting | - |
dc.type | Article | - |
dc.identifier.wosid | 000523746000019 | - |
dc.identifier.scopusid | 2-s2.0-85079681600 | - |
dc.type.rims | ART | - |
dc.citation.volume | 26 | - |
dc.citation.issue | 5 | - |
dc.citation.beginningpage | 2002 | - |
dc.citation.endingpage | 2011 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS | - |
dc.identifier.doi | 10.1109/TVCG.2020.2973050 | - |
dc.contributor.localauthor | Yoon, Sung-Eui | - |
dc.contributor.localauthor | Woo, Woontack | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article; Proceedings Paper | - |
dc.subject.keywordAuthor | Lighting | - |
dc.subject.keywordAuthor | Shape | - |
dc.subject.keywordAuthor | Probes | - |
dc.subject.keywordAuthor | Estimation | - |
dc.subject.keywordAuthor | Virtual reality | - |
dc.subject.keywordAuthor | Image reconstruction | - |
dc.subject.keywordAuthor | Cameras | - |
dc.subject.keywordAuthor | Light estimation | - |
dc.subject.keywordAuthor | light probe | - |
dc.subject.keywordAuthor | physically-based rendering | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | coherent rendering | - |
dc.subject.keywordAuthor | mixed reality | - |
dc.subject.keywordPlus | AUGMENTED REALITY | - |
dc.subject.keywordPlus | ILLUMINATION | - |
dc.subject.keywordPlus | REFLECTANCE | - |
dc.subject.keywordPlus | COLOR | - |
dc.subject.keywordPlus | FACES | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.