Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition

TL;DR

Patch-NetVLAD introduces a multi-scale fusion approach for local and global descriptors, significantly improving visual place recognition robustness against appearance and viewpoint changes in real-world environments.

Contribution

It proposes a novel patch-level feature formulation from NetVLAD residuals and a multi-scale fusion method, enhancing invariance and performance over existing descriptors.

Findings

Outperforms existing global and local descriptors on challenging datasets

Achieves state-of-the-art results in visual place recognition

Offers a faster, configurable version suitable for real-time applications

Abstract

Visual Place Recognition is a challenging task for robotics and autonomous systems, which must deal with the twin problems of appearance and viewpoint change in an always changing world. This paper introduces Patch-NetVLAD, which provides a novel formulation for combining the advantages of both local and global descriptor methods by deriving patch-level features from NetVLAD residuals. Unlike the fixed spatial neighborhood regime of existing local keypoint features, our method enables aggregation and matching of deep-learned local features defined over the feature-space grid. We further introduce a multi-scale fusion of patch features that have complementary scales (i.e. patch sizes) via an integral feature space and show that the fused features are highly invariant to both condition (season, structure, and illumination) and viewpoint (translation and rotation) changes. Patch-NetVLAD outperforms both global and local feature descriptor-based methods with comparable compute, achieving state-of-the-art visual place recognition results on a range of challenging real-world datasets, including winning the Facebook Mapillary Visual Place Recognition Challenge at ECCV2020. It is also adaptable to user requirements, with a speed-optimised version operating over an order of magnitude faster than the state-of-the-art. By combining superior performance with improved computational efficiency in a configurable framework, Patch-NetVLAD is well suited to enhance both stand-alone place recognition capabilities and the overall performance of SLAM systems.