3d Image Generation from Single 2d Image using Monocular Depth Cues
B. Gnana Priya1, M. Arulselvi2
1B. Gnana Priya, Assistant Professor, Department of Computer Science and Engineering Annamalai University.
2Dr. M. Arulselvi, Associate Professor, Department of Computer Science and Engineering Annamalai University.
Manuscript received on November 26, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 856-859 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3985129219/2020©BEIESP | DOI: 10.35940/ijeat.B3985.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: There has been a tremendous increase in the popularity of 3D hardware such as TV’s, Smartphone’s, gadgets for gaming, medical equipments, 3D printing and many more. 2D to 3D conversion is applied at various levels to get 3D content. In this paper, 3D image is generated from a single 2D image. we try to convert our own Karate and Bharathanatyam (KB) Dataset which contains both indoor and outdoor poses to 3D. Here, Watershed algorithm is employed to segment the image. Depth map is generated by sharpness and contrast as depth cues. The 3D image from single 2D image is created by depth image based rendering method.
Keywords: 2D to 3D conversion image conversion, Depth cues, DIBR, KB Dataset, 3D Basics, Watershed algorithm.