DC-VLAQ: Query-Residual Aggregation for Robust Visual Place Recognition

TL;DR

DC-VLAQ introduces a novel fusion and global aggregation framework for visual place recognition, enhancing robustness against viewpoint, illumination, and domain shifts by leveraging complementary features and residual query schemes.

Contribution

The paper presents DC-VLAQ, a new representation-centric approach combining residual-guided fusion of VFMs with a residual global aggregation scheme for improved VPR performance.

Findings

Outperforms existing methods on multiple benchmarks

Achieves state-of-the-art results under domain shifts

Demonstrates robustness to appearance changes

Abstract

One of the central challenges in visual place recognition (VPR) is learning a robust global representation that remains discriminative under large viewpoint changes, illumination variations, and severe domain shifts. While visual foundation models (VFMs) provide strong local features, most existing methods rely on a single model, overlooking the complementary cues offered by different VFMs. However, exploiting such complementary information inevitably alters token distributions, which challenges the stability of existing query-based global aggregation schemes. To address these challenges, we propose DC-VLAQ, a representation-centric framework that integrates the fusion of complementary VFMs and robust global aggregation. Specifically, we first introduce a lightweight residual-guided complementary fusion that anchors representations in the DINOv2 feature space while injecting complementary semantics from CLIP through a learned residual correction. In addition, we propose the Vector of Local Aggregated Queries (VLAQ), a query--residual global aggregation scheme that encodes local tokens by their residual responses to learnable queries, resulting in improved stability and the preservation of fine-grained discriminative cues. Extensive experiments on standard VPR benchmarks, including Pitts30k, Tokyo24/7, MSLS, Nordland, SPED, and AmsterTime, demonstrate that DC-VLAQ consistently outperforms strong baselines and achieves state-of-the-art performance, particularly under challenging domain shifts and long-term appearance changes.