EmbodiedPlace: Learning Mixture-of-Features with Embodied Constraints for Visual Place Recognition

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Bingxi, Chen, Hao, Guo, Shiyi, Wu, Yihong, Cui, Jinqiang, Zhang, Hong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916795349204992
author Liu, Bingxi
Chen, Hao
Guo, Shiyi
Wu, Yihong
Cui, Jinqiang
Zhang, Hong
author_facet Liu, Bingxi
Chen, Hao
Guo, Shiyi
Wu, Yihong
Cui, Jinqiang
Zhang, Hong
contents Visual Place Recognition (VPR) is a scene-oriented image retrieval problem in computer vision in which re-ranking based on local features is commonly employed to improve performance. In robotics, VPR is also referred to as Loop Closure Detection, which emphasizes spatial-temporal verification within a sequence. However, designing local features specifically for VPR is impractical, and relying on motion sequences imposes limitations. Inspired by these observations, we propose a novel, simple re-ranking method that refines global features through a Mixture-of-Features (MoF) approach under embodied constraints. First, we analyze the practical feasibility of embodied constraints in VPR and categorize them according to existing datasets, which include GPS tags, sequential timestamps, local feature matching, and self-similarity matrices. We then propose a learning-based MoF weight-computation approach, utilizing a multi-metric loss function. Experiments demonstrate that our method improves the state-of-the-art (SOTA) performance on public datasets with minimal additional computational overhead. For instance, with only 25 KB of additional parameters and a processing time of 10 microseconds per frame, our method achieves a 0.9\% improvement over a DINOv2-based baseline performance on the Pitts-30k test set.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13133
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EmbodiedPlace: Learning Mixture-of-Features with Embodied Constraints for Visual Place Recognition
Liu, Bingxi
Chen, Hao
Guo, Shiyi
Wu, Yihong
Cui, Jinqiang
Zhang, Hong
Computer Vision and Pattern Recognition
Visual Place Recognition (VPR) is a scene-oriented image retrieval problem in computer vision in which re-ranking based on local features is commonly employed to improve performance. In robotics, VPR is also referred to as Loop Closure Detection, which emphasizes spatial-temporal verification within a sequence. However, designing local features specifically for VPR is impractical, and relying on motion sequences imposes limitations. Inspired by these observations, we propose a novel, simple re-ranking method that refines global features through a Mixture-of-Features (MoF) approach under embodied constraints. First, we analyze the practical feasibility of embodied constraints in VPR and categorize them according to existing datasets, which include GPS tags, sequential timestamps, local feature matching, and self-similarity matrices. We then propose a learning-based MoF weight-computation approach, utilizing a multi-metric loss function. Experiments demonstrate that our method improves the state-of-the-art (SOTA) performance on public datasets with minimal additional computational overhead. For instance, with only 25 KB of additional parameters and a processing time of 10 microseconds per frame, our method achieves a 0.9\% improvement over a DINOv2-based baseline performance on the Pitts-30k test set.
title EmbodiedPlace: Learning Mixture-of-Features with Embodied Constraints for Visual Place Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.13133