DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Soo Ye | ko |
dc.contributor.author | Kim, Munchurl | ko |
dc.date.accessioned | 2018-12-20T01:56:35Z | - |
dc.date.available | 2018-12-20T01:56:35Z | - |
dc.date.created | 2018-12-01 | - |
dc.date.created | 2018-12-01 | - |
dc.date.created | 2018-12-01 | - |
dc.date.issued | 2018-12-05 | - |
dc.identifier.citation | 14th Asian Conference on Computer Vision (ACCV), pp.395 - 409 | - |
dc.identifier.uri | http://hdl.handle.net/10203/247207 | - |
dc.description.abstract | While inverse tone mapping (ITM) was frequently used for graphics rendering in the high dynamic range (HDR) space, the advent of HDR TVs and the consequent need for HDR multimedia contents open up new horizons for the consumption of ultra-high quality video contents. Unfortunately, previous methods are not appropriate for HDR TVs, and their inverse-tone-mapped results are not visually pleasing with noise amplification or lack of details. In this paper, we first present the ITM problem for HDR TVs and propose a CNN-based architecture, called ITM-CNN, which restores lost details and local contrast with its training strategy for enhancing the performance based on image decomposition using the guided filter. We demonstrate the benefits of decomposing the image by experimenting with various architectures and also compare the performance for different training strategies. Our ITM-CNN is a powerful means to solve the lack of HDR video contents with legacy LDR videos. | - |
dc.language | English | - |
dc.publisher | Asian Conference on Computer Vision (ACCV) | - |
dc.title | ITM-CNN: Learning the Inverse Tone Mapping from Low Dynamic Range Video to High Dynamic Range Displays using Convolutional Neural Networks | - |
dc.type | Conference | - |
dc.identifier.wosid | 000492903100025 | - |
dc.identifier.scopusid | 2-s2.0-85067227771 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 395 | - |
dc.citation.endingpage | 409 | - |
dc.citation.publicationname | 14th Asian Conference on Computer Vision (ACCV) | - |
dc.identifier.conferencecountry | AT | - |
dc.identifier.conferencelocation | Perth Convention and Exhibition Centre | - |
dc.identifier.doi | 10.1007/978-3-030-20893-6_25 | - |
dc.contributor.localauthor | Kim, Munchurl | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.