DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image release_tdbjw6rn5bch3kuidapivqgsd4

by Andrey Kurenkov, Jingwei Ji, Animesh Garg, Viraj Mehta, JunYoung Gwak, Christopher Choy, Silvio Savarese

Released as a article .

2017  

Abstract

3D reconstruction from a single image is a key problem in multiple applications ranging from robotic manipulation to augmented reality. Prior methods have tackled this problem through generative models which predict 3D reconstructions as voxels or point clouds. However, these methods can be computationally expensive and miss fine details. We introduce a new differentiable layer for 3D data deformation and use it in DeformNet to learn a model for 3D reconstruction-through-deformation. DeformNet takes an image input, searches the nearest shape template from a database, and deforms the template to match the query image. We evaluate our approach on the ShapeNet dataset and show that - (a) the Free-Form Deformation layer is a powerful new building block for Deep Learning models that manipulate 3D data (b) DeformNet uses this FFD layer combined with shape retrieval for smooth and detail-preserving 3D reconstruction of qualitatively plausible point clouds with respect to a single query image (c) compared to other state-of-the-art 3D reconstruction methods, DeformNet quantitatively matches or outperforms their benchmarks by significant margins. For more information, visit: https://deformnet-site.github.io/DeformNet-website/ .
In text/plain format

Archived Files and Locations

application/pdf  1.3 MB
file_ktg6wo2bgfe5dhwcdkyyugt3iq
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-08-11
Version   v1
Language   en ?
arXiv  1708.04672v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 4fc198fd-b2e7-42bb-a9f5-be17aec4f752
API URL: JSON