Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery

Abstract

Visual Place Recognition (VPR) is a crucial component of 6-DoF localization, visual SLAM and structure-from-motion pipelines, tasked to generate an initial list of place match hypotheses by matching global place descriptors. However, commonly-used CNN-based methods either process multiple image resolutions after training or use a single resolution and limit multi-scale feature extraction to the last convolutional layer during training. In this paper, we augment NetVLAD representation learning with low-resolution image pyramid encoding which leads to richer place representations. The resultant multi-resolution feature pyramid can be conveniently aggregated through VLAD into a single compact representation, avoiding the need for concatenation or summation of multiple patches in recent multi-scale approaches. Furthermore, we show that the underlying learnt feature tensor can be combined with existing multi-scale approaches to improve their baseline performance. Evaluation on 15 viewpoint-

Stats

• citations47
• S2 citations—
• github stars49
• HF likes0
• heat score16.01
• arxiv keykhaliq2022multires

Related papers

• Pointnetvlad: Deep Point Cloud Based Retrieval For Large-scale Place Recognition (2018)25.45
• Optimal Transport Aggregation For Visual Place Recognition (2023)20.51
• Data-efficient Large Scale Place Recognition With Graded Similarity Supervision (2023)16.32
• Mixvpr: Feature Mixing For Visual Place Recognition (2023)22.68
• Unipr-3d: Towards Universal Visual Place Recognition With Visual Geometry Grounded Transformer (2025)2.95
• Lavpr: Benchmarking Language And Vision For Place Recognition (2026)2.35
• Structured Pruning For Efficient Visual Place Recognition (2024)2.26
• Vlad-buff: Burst-aware Fast Feature Aggregation For Visual Place Recognition (2024)10.46