Back to Search
Start Over
P‐4.13: Flexible multi‐view synthesis from a single image.
- Source :
- SID Symposium Digest of Technical Papers; Apr2024 Suppl 1, Vol. 55 Issue 1, p800-803, 4p
- Publication Year :
- 2024
-
Abstract
- This paper proposes a multi‐view autostereoscopic content synthesis technique for glasses‐free 3D display devices. This technology uses deep learning methods to construct 3D implicit representations to ensure geometric consistency between viewpoints. At inferencing time, our method takes a single RGB image as input and generates a 3D implicit representation of the input view frustum. When rendering new viewpoints, the size of the 3D content's parallax, the screen‐in/out ratio, and the number of viewpoints can be adjusted by setting the external parameters of the virtual camera. Thus, it can adapt to glasses‐free 3D display devices with different optical designs. [ABSTRACT FROM AUTHOR]
- Subjects :
- DEEP learning
OPTICAL devices
PARALLAX
DIGITAL cameras
Subjects
Details
- Language :
- English
- ISSN :
- 0097966X
- Volume :
- 55
- Issue :
- 1
- Database :
- Complementary Index
- Journal :
- SID Symposium Digest of Technical Papers
- Publication Type :
- Academic Journal
- Accession number :
- 178132420
- Full Text :
- https://doi.org/10.1002/sdtp.17206