TY  - CONF
AU  - Hugo Bertiche
AU  - Meysam Madadi
AU  - Sergio Escalera
A2  - FG
PY  - 2021//
TI  - Deep Parametric Surfaces for 3D Outfit Reconstruction from Single View Image
BT  - 16th IEEE International Conference on Automatic Face and Gesture Recognition
SP  - 1
EP  - 8
N2  - We present a methodology to retrieve analytical surfaces parametrized as a neural network. Previous works on 3D reconstruction yield point clouds, voxelized objects or meshes. Instead, our approach yields 2-manifolds in the euclidean space through deep learning. To this end, we implement a novel formulation for fully connected layers as parametrized manifolds that allows continuous predictions with differential geometry. Based on this property we propose a novel smoothness loss. Results on CLOTH3D++ dataset show the possibility to infer different topologies and the benefits of the smoothness term based on differential geometry.
UR  - https://ieeexplore.ieee.org/document/9667017
L1  - http://refbase.cvc.uab.es/files/BME2021.pdf
UR  - http://dx.doi.org/10.1109/FG52635.2021.9667017
N1  - HUPBA; no proj
ID  - Hugo Bertiche2021
ER  -