An Efficient End-to-End 3D Voxel Reconstruction based on Neural Architecture Search

TL;DR

This paper introduces an efficient end-to-end 3D voxel reconstruction method that uses neural architecture search to optimize network design, achieving higher accuracy with fewer parameters than traditional methods.

Contribution

It proposes a novel neural architecture search framework for 3D voxel reconstruction that eliminates the need for post-processing surface algorithms.

Findings

Achieves higher reconstruction accuracy than existing methods.

Uses fewer network parameters for complex 3D models.

Provides an end-to-end pipeline without traditional surface reconstruction algorithms.

Abstract

Using neural networks to represent 3D objects has become popular. However, many previous works employ neural networks with fixed architecture and size to represent different 3D objects, which lead to excessive network parameters for simple objects and limited reconstruction accuracy for complex objects. For each 3D model, it is desirable to have an end-to-end neural network with as few parameters as possible to achieve high-fidelity reconstruction. In this paper, we propose an efficient voxel reconstruction method utilizing neural architecture search (NAS) and binary classification. Taking the number of layers, the number of nodes in each layer, and the activation function of each layer as the search space, a specific network architecture can be obtained based on reinforcement learning technology. Furthermore, to get rid of the traditional surface reconstruction algorithms (e.g., marching cube) used after network inference, we complete the end-to-end network by classifying binary voxels. Compared to other signed distance field (SDF) prediction or binary classification networks, our method achieves significantly higher reconstruction accuracy using fewer network parameters.