3D ShapeNets: A deep representation for volumetric shapes
Top Cited Papers
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1912-1920
- https://doi.org/10.1109/cvpr.2015.7298801
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.Keywords
Other Versions
This publication has 20 references indexed in Scilit:
- Structure recovery by part assemblyACM Transactions on Graphics, 2012
- The Shape Boltzmann Machine: A strong model of object shapePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- SUN database: Large-scale scene recognition from abbey to zooPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Using fast weights to improve persistent contrastive divergencePublished by Association for Computing Machinery (ACM) ,2009
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- The princeton shape benchmarkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Modeling by exampleACM Transactions on Graphics, 2004
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992