19 June 2017 Progressive 3D shape abstraction via hierarchical CSG tree
Author Affiliations +
Proceedings Volume 10443, Second International Workshop on Pattern Recognition; 1044315 (2017) https://doi.org/10.1117/12.2280270
Event: Second International Workshop on Pattern Recognition, 2017, Singapore, Singapore
Abstract
A constructive solid geometry(CSG) tree model is proposed to progressively abstract 3D geometric shape of general object from 2D image. Unlike conventional ones, our method applies to general object without the need for massive CAD models, and represents the object shapes in a coarse-to-fine manner that allows users to view temporal shape representations at any time. It stands in a transitional position between 2D image feature and CAD model, benefits from state-of-the-art object detection approaches and better initializes CAD model for finer fitting, estimates 3D shape and pose parameters of object at different levels according to visual perception objective, in a coarse-to-fine manner. Two main contributions are the application of CSG building up procedure into visual perception, and the ability of extending object estimation result into a more flexible and expressive model than 2D/3D primitive shapes. Experimental results demonstrate the feasibility and effectiveness of the proposed approach.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xingyou Chen, Xingyou Chen, Jin Tang, Jin Tang, Chenglong Li, Chenglong Li, } "Progressive 3D shape abstraction via hierarchical CSG tree", Proc. SPIE 10443, Second International Workshop on Pattern Recognition, 1044315 (19 June 2017); doi: 10.1117/12.2280270; https://doi.org/10.1117/12.2280270
PROCEEDINGS
6 PAGES


SHARE
Back to Top