3D ShapeNets for 2.5D Object Recognition and Next-Best-View Prediction
Authors:
- Xiaoou TangXTXiaoou Tang
Preprint
Abstract
3D shape is a crucial but heavily underutilized cue in object recognition, mostly due to the lack of a good generic shape representation. With the recent boost of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect), it is even more urgent to have a useful 3D shape model in an object recognition pipeline. Furthermore, when the recognition has low confidence, it is important to have a fail-safe mode for object recognition systems to intelligently choose the best view to obtain extra observation from another viewpoint, in order to reduce the uncertainty as much as possible. 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 naturally supports object recognition from 2.5D depth map, and it is the first model that supports view planning for object recognition. We construct a large-scale 3D computer graphics dataset to train our model, and conduct extensive experiments to study this new representation.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Predicting Failures of Vision Systems2014
- The Shape Boltzmann Machine: A Strong Model of Object ShapeInternational Journal of Computer Vision, 2013
- A textured object recognition pipeline for color and depth image data2012
- A Practical Guide to Training Restricted Boltzmann Machines2012
- Unsupervised learning of hierarchical representations with convolutional deep belief networksCommunications of the ACM, 2011
- SUN database: Large-scale scene recognition from abbey to zoo2010
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Using fast weights to improve persistent contrastive divergence2009
- 3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial ConstraintsInternational Journal of Computer Vision, 2006
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992