Higher Order Function Networks for View Planning and Multi-View Reconstruction

TL;DR

This paper introduces a neural network-based view planning method using Higher Order Functions for multi-view 3D reconstruction, balancing efficiency and accuracy without requiring a prior 3D model.

Contribution

It extends HOF-based shape representation to multiple images and develops a view planning approach that minimizes the number of views needed for reconstruction.

Findings

Achieves near-optimal view efficiency compared to offline methods.

Does not require prior object models, enabling online application.

Performs well even on unseen object classes.

Abstract

We consider the problem of planning views for a robot to acquire images of an object for visual inspection and reconstruction. In contrast to offline methods which require a 3D model of the object as input or online methods which rely on only local measurements, our method uses a neural network which encodes shape information for a large number of objects. We build on recent deep learning methods capable of generating a complete 3D reconstruction of an object from a single image. Specifically, in this work, we extend a recent method which uses Higher Order Functions (HOF) to represent the shape of the object. We present a new generalization of this method to incorporate multiple images as input and establish a connection between visibility and reconstruction quality. This relationship forms the foundation of our view planning method where we compute viewpoints to visually cover the output of the multi-view HOF network with as few images as possible. Experiments indicate that our method provides a good compromise between online and offline methods: Similar to online methods, our method does not require the true object model as input. In terms of number of views, it is much more efficient. In most cases, its performance is comparable to the optimal offline case even on object classes the network has not been trained on.