Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction

Rohan Chabra, Jan Eric Lenssen, Eddy Ilg, Tanner Schmidt, Julian Straub, Steven Lovegrove, Richard Newcombe

3/24/2020

Keywords: Generalization, Voxel Grid, Local Conditioning

Venue: ECCV 2020

Bibtex: @inproceedings{chabra2020deepls, booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)}, author = {Rohan Chabra and Jan Eric Lenssen and Eddy Ilg and Tanner Schmidt and Julian Straub and Steven Lovegrove and Richard Newcombe}, title = {Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction}, year = {2020}, url = {http://arxiv.org/abs/2003.10983v3}, entrytype = {inproceedings}, id = {chabra2020deepls} }

Abstract

Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a deep shape representation that enables encoding and reconstruction of high-quality 3D shapes without prohibitive memory requirements. DeepLS replaces the dense volumetric signed distance function (SDF) representation used in traditional surface reconstruction systems with a set of locally learned continuous SDFs defined by a neural network, inspired by recent work such as DeepSDF. Unlike DeepSDF, which represents an object-level SDF with a neural network and a single latent code, we store a grid of independent latent codes, each responsible for storing information about surfaces in a small local neighborhood. This decomposition of scenes into local shapes simplifies the prior distribution that the network must learn, and also enables efficient inference. We demonstrate the effectiveness and generalization power of DeepLS by showing object shape encoding and reconstructions of full scenes, where DeepLS delivers high compression, accuracy, and local shape completion.

Citation Graph
(Double click on nodes to open corresponding papers' pages)

* Showing citation graph for papers within our database. Data retrieved from Semantic Scholar. For full citation graphs, visit ConnectedPapers.