Systematic Evaluation of Novel View Synthesis for Video Place Recognition

TL;DR

This paper systematically evaluates how synthetic novel views influence video place recognition performance, showing small improvements with added views and highlighting factors like number of views and dataset imagery.

Contribution

It provides a comprehensive analysis of the impact of synthetic novel views on VPR, comparing multiple datasets and similarity methods.

Findings

Small synthetic view additions improve VPR recognition.

Larger view additions depend more on number of views than viewpoint change.

Type of imagery affects the effectiveness of synthetic views.

Abstract

The generation of synthetic novel views has the potential to positively impact robot navigation in several ways. In image-based navigation, a novel overhead view generated from a scene taken by a ground robot could be used to guide an aerial robot to that location. In Video Place Recognition (VPR), novel views of ground locations from the air can be added that enable a UAV to identify places seen by the ground robot, and similarly, overhead views can be used to generate novel ground views. This paper presents a systematic evaluation of synthetic novel views in VPR using five public VPR image databases and seven typical image similarity methods. We show that for small synthetic additions, novel views improve VPR recognition statistics. We find that for larger additions, the magnitude of viewpoint change is less important than the number of views added and the type of imagery in the dataset.