Geometry-Aware Network for Non-Rigid Shape Prediction From a Single View

Albert Pumarola, Antonio Agudo, Lorenzo Porzi, Alberto Sanfeliu, Vincent Lepetit, Francesc Moreno-Noguer; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4681-4690

Abstract


We propose a method for predicting the 3D shape of a deformable surface from a single view. By contrast with previous approaches, we do not need a pre-registered template of the surface, and our method is robust to the lack of texture and partial occlusions. At the core of our approach is a geometry-aware deep architecture that tackles the problem as usually done in analytic solutions: first perform 2D detection of the mesh and then estimate a 3D shape that is geometrically consistent with the image. We train this architecture in an end-to-end manner using a large dataset of synthetic renderings of shapes under different levels of deformation, material properties, textures and lighting conditions. We evaluate our approach on a test split of this dataset and available real benchmarks, consistently improving state-of-the-art solutions with a significantly lower computational time.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pumarola_2018_CVPR,
author = {Pumarola, Albert and Agudo, Antonio and Porzi, Lorenzo and Sanfeliu, Alberto and Lepetit, Vincent and Moreno-Noguer, Francesc},
title = {Geometry-Aware Network for Non-Rigid Shape Prediction From a Single View},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}