Multiresolution Deep Implicit Functions for 3D Shape Representation

TL;DR

This paper presents MDIF, a hierarchical deep implicit function model that captures multi-level detail in 3D shapes and enhances shape completion through a novel latent grid dropout technique, outperforming previous methods.

Contribution

Introduces MDIF, the first deep implicit model supporting multi-resolution detail, flexible inference modes, and high-quality shape completion.

Findings

Superior accuracy in 3D shape reconstruction

Effective shape completion with latent grid dropout

Supports both encoder-decoder and decoder-only inference modes

Abstract

We introduce Multiresolution Deep Implicit Functions (MDIF), a hierarchical representation that can recover fine geometry detail, while being able to perform global operations such as shape completion. Our model represents a complex 3D shape with a hierarchy of latent grids, which can be decoded into different levels of detail and also achieve better accuracy. For shape completion, we propose latent grid dropout to simulate partial data in the latent space and therefore defer the completing functionality to the decoder side. This along with our multires design significantly improves the shape completion quality under decoder-only latent optimization. To the best of our knowledge, MDIF is the first deep implicit function model that can at the same time (1) represent different levels of detail and allow progressive decoding; (2) support both encoder-decoder inference and decoder-only latent optimization, and fulfill multiple applications; (3) perform detailed decoder-only shape completion. Experiments demonstrate its superior performance against prior art in various 3D reconstruction tasks.