Skip to main content

3D ShapeNets: A deep representation for volumetric shapes

Author(s): Wu, Zhirong; Song, Shuran; Khosla, Aditya; Yu, Fisher; Zhang, Linguang; et al

To refer to this page use:
Abstract: 3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the recent availability of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect), it is becoming increasingly important to have a powerful 3D shape representation in the loop. Apart from category recognition, recovering full 3D shapes from view-based 2.5D depth maps is also a critical part of visual understanding. To this end, we propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network. Our model, 3D ShapeNets, learns the distribution of complex 3D shapes across different object categories and arbitrary poses from raw CAD data, and discovers hierarchical compositional part representation automatically. It naturally supports joint object recognition and shape completion from 2.5D depth maps, and it enables active object recognition through view planning. To train our 3D deep learning model, we construct ModelNet - a large-scale 3D CAD model dataset. Extensive experiments show that our 3D deep representation enables significant performance improvement over the-state-of-the-arts in a variety of tasks.
Publication Date: 2015
Citation: Wu, Zhirong, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. "3D ShapeNets: A deep representation for volumetric shapes." In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015). doi: 10.1109/CVPR.2015.7298801
DOI: 10.1109/CVPR.2015.7298801
ISSN: 1063-6919
Type of Material: Conference Article
Journal/Proceeding Title: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.