Local Deep Implicit Functions for 3D Shape

TL;DR

This paper introduces Local Deep Implicit Functions (LDIF), a novel 3D shape representation that improves surface reconstruction accuracy, reduces network complexity, and enhances generalization across diverse shape categories.

Contribution

The paper proposes LDIF, a structured decomposition of space into learned implicit functions, enabling accurate, compact, and consistent 3D shape reconstructions from various inputs.

Findings

10.3 points higher surface reconstruction accuracy than OccNet

Fewer than 1% of the network parameters of previous methods

15.8 and 17.8 point improvements in depth image completion and generalization

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.