상세정보
학술지
High-Precision Depth Map Estimation from Missing Viewpoints for 360-Degree Digital Holography
- 저자
- 김학동, 임헌영, 지민규, 이유림, 윤민성, 김청원
- 발행일
- 202209
- 출처
- Applied Sciences, v.12 no.19, pp.1-20
- ISSN
- 2076-3417
- 출판사
- MDPI
- 협약과제
- 21MH1300, 홀로그램콘텐츠 서비스센터 운영, 지형근
- 초록
- In this paper, we propose a novel model to extract highly precise depth maps from missing viewpoints, especially for generating holographic 3D content. These depth maps are essential elements for phase extraction, which is required for the synthesis of computer-generated holograms (CGHs). The proposed model, called the holographic dense depth, estimates depth maps through feature extraction, combining up-sampling. We designed and prepared a total of 9832 multi-view images with resolutions of 640 × 360. We evaluated our model by comparing the estimated depth maps with their ground truths using various metrics. We further compared the CGH patterns created from estimated depth maps with those from ground truths and reconstructed the holographic 3D image scenes from their CGHs. Both quantitative and qualitative results demonstrate the effectiveness of the proposed method.
- KSP 제안 키워드
- 360-degree, 3D Image, 3D content, Computer generated holograms(CGH), Dense depth, Depth map estimation, Essential element, Feature extractioN, Novel model, Proposed model, digital holography
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
