3D-R2N2: 3D Recurrent Reconstruction
@inproceedings{choy20163d,
title={3d-r2n2: A unified approach for single and multi-view 3d object reconstruction},
author={Choy, Christopher B and Xu, Danfei and Gwak, JunYoung and Chen, Kevin and Savarese, Silvio},
booktitle={European conference on computer vision},
pages={628--644},
year={2016},
organization={Springer}
}
- Multi-view images -> 3D volumetric occupancy grid
- Recurrent Neural Network to fuse multiple color images
- LSTM stands for “Long short-term memory”