Retrieving 3D Objects with Articulated Limbs by Depth Image Input

Jun-Yang Lin, May-Fang She, Ming-Han Tsai, I-Chen Lin, Yo-Chung Lau, Hsu-Hang Liu

Abstract

Existing 3D model retrieval approaches usually implicitly assume that the target models are rigid-body. When they are applied to retrieving articulated models, the retrieved results are substantially influenced by the model postures. This paper presents a novel approach to retrieve 3D models from a database based on one or few input depth images. While related methods compared the inputs with whole shapes of 3D model projections at certain viewpoints, the proposed method extracts the limbs and torso regions from projections and analyzes the features of local regions. The use of both global and local features can alleviate the disturbance of model postures in model retrieval. Therefore, the system can retrieve models of an identical category but in different postures. Our experiments demonstrate that this approach can efficiently retrieve relevant models within a second, and it provides higher retrieval accuracy than those of compared methods for rigid 3D models or models with articulated limbs.

Download


Paper Citation


in Harvard Style

Lin J., She M., Tsai M., Lin I., Lau Y. and Liu H. (2018). Retrieving 3D Objects with Articulated Limbs by Depth Image Input.In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, ISBN 978-989-758-287-5, pages 101-111. DOI: 10.5220/0006609601010111


in Bibtex Style

@conference{grapp18,
author={Jun-Yang Lin and May-Fang She and Ming-Han Tsai and I-Chen Lin and Yo-Chung Lau and Hsu-Hang Liu},
title={Retrieving 3D Objects with Articulated Limbs by Depth Image Input},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,},
year={2018},
pages={101-111},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006609601010111},
isbn={978-989-758-287-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,
TI - Retrieving 3D Objects with Articulated Limbs by Depth Image Input
SN - 978-989-758-287-5
AU - Lin J.
AU - She M.
AU - Tsai M.
AU - Lin I.
AU - Lau Y.
AU - Liu H.
PY - 2018
SP - 101
EP - 111
DO - 10.5220/0006609601010111