Data Driven SVBRDF Estimation Using Deep Embedded Clustering
Photo-realistic representation in user-specified view and lighting conditions is a challenging but high-demand technology in the digital transformation of cultural heritages. Despite recent advances in neural renderings, it is still necessary to capture high-quality surface reflectance from photogra...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/19/3239 |
| _version_ | 1797479758536114176 |
|---|---|
| author | Yong Hwi Kim Kwan H. Lee |
| author_facet | Yong Hwi Kim Kwan H. Lee |
| author_sort | Yong Hwi Kim |
| collection | DOAJ |
| description | Photo-realistic representation in user-specified view and lighting conditions is a challenging but high-demand technology in the digital transformation of cultural heritages. Despite recent advances in neural renderings, it is still necessary to capture high-quality surface reflectance from photography in a controlled environment for real-time applications such as VR/AR and digital arts. In this paper, we present a deep embedding clustering network for spatially-varying bidirectional reflectance distribution function (SVBRDF) estimation. Our network is designed to simultaneously update the reflectance basis and its linear manifold in the spatial domain of SVBRDF. We show that our dual update scheme excels in optimizing the rendering loss in terms of the convergence speed and visual quality compared to the current iterative SVBRDF update methods. |
| first_indexed | 2024-03-09T21:50:25Z |
| format | Article |
| id | doaj.art-ed58f618ef1b4615b6badbbe43f9248f |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T21:50:25Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-ed58f618ef1b4615b6badbbe43f9248f2023-11-23T20:08:43ZengMDPI AGElectronics2079-92922022-10-011119323910.3390/electronics11193239Data Driven SVBRDF Estimation Using Deep Embedded ClusteringYong Hwi Kim0Kwan H. Lee1IT Convergence Components Research Center, Korea Electronics Technology Institute (KETI), Gwangju 61005, KoreaSchool of Mechanical Engineering, Gwangju Institute of Science and Technology (GIST), Gwangju 61005, KoreaPhoto-realistic representation in user-specified view and lighting conditions is a challenging but high-demand technology in the digital transformation of cultural heritages. Despite recent advances in neural renderings, it is still necessary to capture high-quality surface reflectance from photography in a controlled environment for real-time applications such as VR/AR and digital arts. In this paper, we present a deep embedding clustering network for spatially-varying bidirectional reflectance distribution function (SVBRDF) estimation. Our network is designed to simultaneously update the reflectance basis and its linear manifold in the spatial domain of SVBRDF. We show that our dual update scheme excels in optimizing the rendering loss in terms of the convergence speed and visual quality compared to the current iterative SVBRDF update methods.https://www.mdpi.com/2079-9292/11/19/3239SVBRDFdeep embedding clusteringappearance capturesurface reflectance estimation |
| spellingShingle | Yong Hwi Kim Kwan H. Lee Data Driven SVBRDF Estimation Using Deep Embedded Clustering Electronics SVBRDF deep embedding clustering appearance capture surface reflectance estimation |
| title | Data Driven SVBRDF Estimation Using Deep Embedded Clustering |
| title_full | Data Driven SVBRDF Estimation Using Deep Embedded Clustering |
| title_fullStr | Data Driven SVBRDF Estimation Using Deep Embedded Clustering |
| title_full_unstemmed | Data Driven SVBRDF Estimation Using Deep Embedded Clustering |
| title_short | Data Driven SVBRDF Estimation Using Deep Embedded Clustering |
| title_sort | data driven svbrdf estimation using deep embedded clustering |
| topic | SVBRDF deep embedding clustering appearance capture surface reflectance estimation |
| url | https://www.mdpi.com/2079-9292/11/19/3239 |
| work_keys_str_mv | AT yonghwikim datadrivensvbrdfestimationusingdeepembeddedclustering AT kwanhlee datadrivensvbrdfestimationusingdeepembeddedclustering |