Local Deep Implicit Functions for 3D Shape

Abstract

The goal of this project is to learn a 3D shape representation that enables accurate surface reconstruction, compact storage, efficient computation, consistency for similar shapes, generalization across diverse shape categories, and inference from depth camera observations. Towards this end, we introduce Local Deep Implicit Functions (LDIF), a 3D shape representation that decomposes space into a structured set of learned implicit functions. We provide networks that infer the space decomposition and local deep implicit functions from a 3D mesh or posed depth image. During experiments, we find that it provides 10.3 points higher surface reconstruction accuracy (F-Score) than the state-of-the-art (OccNet), while requiring fewer than 1 percent of the network parameters. Experiments on posed depth image completion and generalization to unseen classes show 15.8 and 17.8 point improvements over the state-of-the-art, while producing a structured 3D representation for each input with consistency across diverse shape collections.

Camera ready version for CVPR 2020 Oral. Prior to review, this paper was referred to as DSIF, "Deep Structured Implicit Functions." 11 pages, 9 figures. Project video at https://youtu.be/3RAITzNWVJs

References in corpus (12)

• Deep Residual Learning for Image Recognition
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Learning from Synthetic Humans
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
• Building Statistical Shape Spaces for 3D Human Modeling
• Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
• PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
• A Point Set Generation Network for 3D Object Reconstruction from a Single Image
• GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
• OctNet: Learning Deep 3D Representations at High Resolutions
• OctNetFusion: Learning Depth Fusion from Data

Cited by in corpus (4)

• CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
• NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping
• A Survey on Deep Geometry Learning: From a Representation Perspective
• Learning Signal-Agnostic Manifolds of Neural Fields