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

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 808 - 816
• Main Authors: Shuran Song, Jianxiong Xiao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2016
• Subjects: Feature extraction; Image color analysis; Object detection; Proposals; Shape; Three-dimensional displays; Two dimensional displays

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 bo...