Skip to main content

Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images

Author(s): Song, Shuran; Xiao, Jianxiong

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1bn8p
Abstract: We focus on the task of amodal 3D object detection in RGB-D images, which aims to produce a 3D bounding box of an object in metric form at its full extent. We introduce Deep Sliding Shapes, a 3D ConvNet formulation that takes a 3D volumetric scene from a RGB-D image as input and outputs 3D object bounding boxes. In our approach, we propose the first 3D Region Proposal Network (RPN) to learn objectness from geometric shapes and the first joint Object Recognition Network (ORN) to extract geometric features in 3D and color features in 2D. In particular, we handle objects of various sizes by training an amodal RPN at two different scales and an ORN to regress 3D bounding boxes. Experiments show that our algorithm outperforms the state-of-the-art by 13.8 in mAP and is 200× faster than the original Sliding Shapes.
Publication Date: 2016
Citation: Song, Shuran, and Jianxiong Xiao. "Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images." In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016): pp. 808-816. doi:10.1109/CVPR.2016.94
DOI: 10.1109/CVPR.2016.94
EISSN: 1063-6919
Pages: 808 - 816
Type of Material: Conference Article
Journal/Proceeding Title: 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.