Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
Preprint
Abstract
Understanding the 3D world is a fundamental problem in computer vision. However, learning a good representation of 3D objects is still an open problem due to the high dimensionality of the data and many factors of variation involved. In this work, we investigate the task of single-view 3D object reconstruction from a learning agent's perspective. We formulate the learning process as an interaction between 3D and 2D representations and propose an encoder-decoder network with a novel projection loss defined by the perspective transformation. More importantly, the projection loss enables the unsupervised learning using 2D observation without explicit 3D supervision. We demonstrate the ability of the model in generating 3D volume from a single 2D image with three sets of experiments: (1) learning from single-class objects; (2) learning from multi-class objects and (3) testing on novel object classes. Results show superior performance and better generalization ability for 3D object reconstruction when the projection loss is involved.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Single Image 3D Interpreter Network2016
- Learning a Predictable and Generative Vector Representation for Objects2016
- 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction2016
- Volumetric and Multi-view CNNs for Object Classification on 3D Data2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- 3D ShapeNets: A deep representation for volumetric shapes2015
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations2009
- Unsupervised Learning of Image Transformations2007
- A Theory of Shape by Space CarvingInternational Journal of Computer Vision, 2000