Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Systematic Evaluation of Novel View Synthesis for Video Place Recognition

Muhammad Zawad Mahmud, Samiha Islam, Damian Lyons

TL;DR

It is shown that for small synthetic additions, novel views improve VPR recognition statistics, and 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.

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.

Systematic Evaluation of Novel View Synthesis for Video Place Recognition

TL;DR

It is shown that for small synthetic additions, novel views improve VPR recognition statistics, and 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.

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.
Paper Structure (13 sections, 3 figures, 4 tables)

This paper contains 13 sections, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Literature
  3. Approach
  4. Genwarp
  5. Methodology
  6. Results
  7. Query versus Reference injection results
  8. Small, Medium and Large Injections
  9. Discussion
  10. Effect of query versus reference injection
  11. Effect of Viewpoint change
  12. Effect of Injection size
  13. Conclusions

Figures (3)

  • Figure 1: Model Architecture of the GenWarp framework (from seo2024genwarp).
  • Figure 2: Methodology for Evaluating Injections of Synthetic Novels Views into VPR
  • Figure 3: Example of Novel Synthetic Views generated for the GardensPoint VPR dataset. Clockwise from TL: Query Image, Reference image, Novel Query with Medium elevation change, Novel Query with Large elevation change.