Do We Need Binary Features for 3D Reconstruction?

TL;DR

This paper evaluates the effectiveness of binary features versus classical SIFT features in 3D reconstruction, revealing that binary features generally underperform in accuracy and completeness despite some computational benefits.

Contribution

It provides a comprehensive comparative study of binary and SIFT features specifically for large-scale 3D reconstruction tasks.

Findings

Binary features are often inferior to SIFT in accuracy and completeness.

Most binary features do not significantly outperform SIFT in computational efficiency.

Not all binary features are suitable for 3D reconstruction applications.

Abstract

Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors. They have been shown with promising results on some real time applications, e.g., SLAM, where the matching operations are relative few. However, in computer vision, there are many applications such as 3D reconstruction requiring lots of matching operations between local features. Therefore, a natural question is that is the binary feature still a promising solution to this kind of applications? To get the answer, this paper conducts a comparative study of binary features and their matching methods on the context of 3D reconstruction in a recently proposed large scale mutliview stereo dataset. Our evaluations reveal that not all binary features are capable of this task. Most of them are inferior to the classical SIFT based method in terms of reconstruction accuracy and completeness with a not significant better computational performance.