Shape Reconstruction Using Differentiable Projections and Deep Priors
Abstract
We investigate the problem of reconstructing shapes from noisy and incomplete projections in the presence of viewpoint uncertainities. The problem is cast as an optimization over the shape given measurements obtained by a projection operator and a prior. We present differentiable projection operators for a number of reconstruction problems which when combined with the deep image prior or shape prior allows efficient inference through gradient descent. We apply our method on a variety of reconstruction problems, such as tomographic reconstruction from a few samples, visual hull reconstruction incorporating view uncertainties, and 3D shape reconstruction from noisy depth maps. Experimental results show that our approach is effective for such shape reconstruction problems, without requiring any task-specific training.
Cite
Text
Gadelha et al. "Shape Reconstruction Using Differentiable Projections and Deep Priors." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00011Markdown
[Gadelha et al. "Shape Reconstruction Using Differentiable Projections and Deep Priors." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/gadelha2019iccv-shape/) doi:10.1109/ICCV.2019.00011BibTeX
@inproceedings{gadelha2019iccv-shape,
title = {{Shape Reconstruction Using Differentiable Projections and Deep Priors}},
author = {Gadelha, Matheus and Wang, Rui and Maji, Subhransu},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/ICCV.2019.00011},
url = {https://mlanthology.org/iccv/2019/gadelha2019iccv-shape/}
}