Local Implicit Grid Representations for 3D Scenes

03/19/2020
by   Chiyu "Max" Jiang, et al.
44

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, complexity, or diversity. In this paper, we introduce Local Implicit Grid Representations, a new 3D shape representation designed for scalability and generality. The motivating idea is that most 3D surfaces share geometric details at some scale – i.e., at a scale smaller than an entire object and larger than a small patch. We train an autoencoder to learn an embedding of local crops of 3D shapes at that size. Then, we use the decoder as a component in a shape optimization that solves for a set of latent codes on a regular grid of overlapping crops such that an interpolation of the decoded local shapes matches a partial or noisy observation. We demonstrate the value of this proposed approach for 3D surface reconstruction from sparse point observations, showing significantly better results than alternative approaches.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 4

page 7

page 8

page 12

page 13

page 14

03/24/2020

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

Efficiently reconstructing complex and intricate surfaces at scale is a ...
12/14/2020

Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds

Shape modeling and reconstruction from raw point clouds of objects stand...
08/04/2020

PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations

Implicit surface representations, such as signed-distance functions, com...
08/19/2021

3D Shapes Local Geometry Codes Learning with SDF

A signed distance function (SDF) as the 3D shape description is one of t...
01/06/2020

Meshlet Priors for 3D Mesh Reconstruction

Estimating a mesh from an unordered set of sparse, noisy 3D points is a ...
03/10/2020

Convolutional Occupancy Networks

Recently, implicit neural representations have gained popularity for lea...
01/12/2017

Surface Reconstruction with Data-driven Exemplar Priors

In this paper, we propose a framework to reconstruct 3D models from raw ...

Code Repositories

convolutional_occupancy_networks

[ECCV'20] Convolutional Occupancy Networks


view repo

conv_occupancy_networks_docker

A docker image of conv occupancy networks


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.