3D Object Reconstruction from a Single Depth View with Adversarial Learning

Bo Yang, Hongkai Wen, Sen Wang, Ronald Clark, Andrew Markham, Niki Trigoni; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 679-688

Abstract


In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks. Unlike the existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid by filling in the occluded/missing regions. The key idea is to combine the generative capabilities of autoencoders and the conditional Generative Adversarial Networks (GAN) framework, to infer accurate and fine-grained 3D structures of objects in high-dimensional voxel space. Extensive experiments on large synthetic datasets show that the proposed 3D-RecGAN significantly outperforms the state of the art in single view 3D object reconstruction, and is able to reconstruct unseen types of objects.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2017_ICCV,
author = {Yang, Bo and Wen, Hongkai and Wang, Sen and Clark, Ronald and Markham, Andrew and Trigoni, Niki},
title = {3D Object Reconstruction from a Single Depth View with Adversarial Learning},
booktitle = {The IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}