Di, Xinhan and Dahyot, Rozenn and Prasad, Mukta (2016) Deep Shape from a Low Number of Silhouettes. Lecture Notes in Computer Science, 9915. ISSN 0302-9743

Preview

Download (5MB) | Preview

Abstract

Despite strong progress in the field of 3D reconstruction from multiple views, holes on objects, transparency of objects and textureless scenes, continue to be open challenges. On the other hand, silhouette based reconstruction techniques ease the dependency of 3d reconstruction on image pixels but need a large number of silhouettes to be available from multiple views. In this paper, a novel end to end pipeline is proposed to produce high quality reconstruction from a low number of silhouettes, the core of which is a deep shape reconstruction architecture. Evaluations on ShapeNet [1] show good quality of reconstruction compared with ground truth.

Item Type:	Article
Additional Information:	Computer Vision – ECCV 2016 Workshops. ECCV 2016. Lecture Notes in Computer Science
Keywords:	Deep 3D reconstruction; End to end architecture; Silhouettes;
Academic Unit:	Faculty of Science and Engineering > Research Institutes > Hamilton Institute
Item ID:	15258
Identification Number:	https://doi.org/10.1007/978-3-319-49409-8_21
Depositing User:	Rozenn Dahyot
Date Deposited:	18 Jan 2022 11:46
Journal or Publication Title:	Lecture Notes in Computer Science
Publisher:	Springer Verlag
Refereed:	Yes
URI:	Publisher

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads