DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Donggun | ko |
dc.contributor.author | Jang, Hyeonjoong | ko |
dc.contributor.author | Kim, Incheol | ko |
dc.contributor.author | Kim, Min Hyuk | ko |
dc.date.accessioned | 2023-11-14T10:03:38Z | - |
dc.date.available | 2023-11-14T10:03:38Z | - |
dc.date.created | 2023-11-14 | - |
dc.date.issued | 2023-06-20 | - |
dc.identifier.citation | Computer Vision and Pattern Recognition, CVPR 2023 | - |
dc.identifier.uri | http://hdl.handle.net/10203/314660 | - |
dc.description.abstract | Dual-pixel photography is monocular RGB-D photography with an ultra-high resolution, enabling many applications in computational photography. However, there are still several challenges to fully utilizing dual-pixel photography. Unlike the conventional stereo pair, the dual pixel exhibits a bidirectional disparity that includes positive and negative values, depending on the focus plane depth in an image. Furthermore, capturing a wide range of dual-pixel disparity requires a shallow depth of field, resulting in a severely blurred image, degrading depth estimation performance. Recently, several data-driven approaches have been proposed to mitigate these two challenges. However, due to the lack of the ground-truth dataset of the dual-pixel disparity, existing data-driven methods estimate either inverse depth or blurriness map. In this work, we propose a self-supervised learning method that learns bidirectional disparity by utilizing the nature of anisotropic blur kernels in dual-pixel photography. We observe that the dual-pixel left/right images have reflective-symmetric anisotropic kernels, so their sum is equivalent to that of a conventional image. We take a self-supervised training approach with the novel kernel-split symmetry loss accounting for the phenomenon. Our method does not rely on a training dataset of dual-pixel disparity that does not exist yet. Our method can estimate a complete disparity map with respect to the focus-plane depth from a dual-pixel image, outperforming the baseline dual-pixel methods. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Spatio-Focal Bidirectional Disparity Estimation from a Dual-Pixel Image | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85172984076 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | Computer Vision and Pattern Recognition, CVPR 2023 | - |
dc.identifier.conferencecountry | CN | - |
dc.identifier.conferencelocation | Vancouver | - |
dc.contributor.localauthor | Kim, Min Hyuk | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.