%0 Conference Proceedings
%T Deep Parametric Surfaces for 3D Outfit Reconstruction from Single View Image
%A Hugo Bertiche
%A Meysam Madadi
%A Sergio Escalera
%B 16th IEEE International Conference on Automatic Face and Gesture Recognition
%D 2021
%F Hugo Bertiche2021
%O HUPBA; no proj
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3640), last updated on Mon, 24 Oct 2022 14:35:08 +0200
%X 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.
%U https://ieeexplore.ieee.org/document/9667017
%U http://refbase.cvc.uab.es/files/BME2021.pdf
%U http://dx.doi.org/10.1109/FG52635.2021.9667017
%P 1-8