Saved in:
Bibliographic Details
Main Authors: Deng, Tianchen, Chen, Xun, Li, Ziming, Shen, Hongming, Wang, Danwei, Civera, Javier, Wang, Hesheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.21078
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908733677764608
author Deng, Tianchen
Chen, Xun
Li, Ziming
Shen, Hongming
Wang, Danwei
Civera, Javier
Wang, Hesheng
author_facet Deng, Tianchen
Chen, Xun
Li, Ziming
Shen, Hongming
Wang, Danwei
Civera, Javier
Wang, Hesheng
contents Visual Place Recognition (VPR) has been traditionally formulated as a single-image retrieval task. Using multiple views offers clear advantages, yet this setting remains relatively underexplored and existing methods often struggle to generalize across diverse environments. In this work we introduce UniPR-3D, the first VPR architecture that effectively integrates information from multiple views. UniPR-3D builds on a VGGT backbone capable of encoding multi-view 3D representations, which we adapt by designing feature aggregators and fine-tune for the place recognition task. To construct our descriptor, we jointly leverage the 3D tokens and intermediate 2D tokens produced by VGGT. Based on their distinct characteristics, we design dedicated aggregation modules for 2D and 3D features, allowing our descriptor to capture fine-grained texture cues while also reasoning across viewpoints. To further enhance generalization, we incorporate both single- and multi-frame aggregation schemes, along with a variable-length sequence retrieval strategy. Our experiments show that UniPR-3D sets a new state of the art, outperforming both single- and multi-view baselines and highlighting the effectiveness of geometry-grounded tokens for VPR. Our code and models will be made publicly available on Github https://github.com/dtc111111/UniPR-3D.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21078
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer
Deng, Tianchen
Chen, Xun
Li, Ziming
Shen, Hongming
Wang, Danwei
Civera, Javier
Wang, Hesheng
Computer Vision and Pattern Recognition
Visual Place Recognition (VPR) has been traditionally formulated as a single-image retrieval task. Using multiple views offers clear advantages, yet this setting remains relatively underexplored and existing methods often struggle to generalize across diverse environments. In this work we introduce UniPR-3D, the first VPR architecture that effectively integrates information from multiple views. UniPR-3D builds on a VGGT backbone capable of encoding multi-view 3D representations, which we adapt by designing feature aggregators and fine-tune for the place recognition task. To construct our descriptor, we jointly leverage the 3D tokens and intermediate 2D tokens produced by VGGT. Based on their distinct characteristics, we design dedicated aggregation modules for 2D and 3D features, allowing our descriptor to capture fine-grained texture cues while also reasoning across viewpoints. To further enhance generalization, we incorporate both single- and multi-frame aggregation schemes, along with a variable-length sequence retrieval strategy. Our experiments show that UniPR-3D sets a new state of the art, outperforming both single- and multi-view baselines and highlighting the effectiveness of geometry-grounded tokens for VPR. Our code and models will be made publicly available on Github https://github.com/dtc111111/UniPR-3D.
title UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.21078