Breaking the Frame: Visual Place Recognition by Overlap Prediction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00380703" target="_blank" >RIV/68407700:21230/25:00380703 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/WACV61041.2025.00232" target="_blank" >https://doi.org/10.1109/WACV61041.2025.00232</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV61041.2025.00232" target="_blank" >10.1109/WACV61041.2025.00232</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Breaking the Frame: Visual Place Recognition by Overlap Prediction

Popis výsledku v původním jazyce

Visual place recognition methods struggle with occlusion and partial visual overlaps. We propose a novel visual place recognition approach based on overlap prediction, called VOP, shifting from traditional reliance on global image similarities and local features to image overlap prediction. VOP proceeds co-visible image sections by obtaining patch-level embeddings using a Vision Transformer backbone and establishing patch-to-patch correspondences without requiring expensive feature detection and matching. Our approach uses a voting mechanism to assess overlap scores for potential database images. It provides a nuanced image retrieval metric in challenging scenarios. Experimental results show that VOP leads to more accurate relative pose estimation and localization results on the retrieved image pairs than state-of-the-art baselines on a number of large-scale, real-world indoor and outdoor benchmarks. The code is available at https: //github.com/weitong8591/vop.git.

Název v anglickém jazyce

Breaking the Frame: Visual Place Recognition by Overlap Prediction

Popis výsledku anglicky

Visual place recognition methods struggle with occlusion and partial visual overlaps. We propose a novel visual place recognition approach based on overlap prediction, called VOP, shifting from traditional reliance on global image similarities and local features to image overlap prediction. VOP proceeds co-visible image sections by obtaining patch-level embeddings using a Vision Transformer backbone and establishing patch-to-patch correspondences without requiring expensive feature detection and matching. Our approach uses a voting mechanism to assess overlap scores for potential database images. It provides a nuanced image retrieval metric in challenging scenarios. Experimental results show that VOP leads to more accurate relative pose estimation and localization results on the retrieved image pairs than state-of-the-art baselines on a number of large-scale, real-world indoor and outdoor benchmarks. The code is available at https: //github.com/weitong8591/vop.git.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

ISBN

979-8-3315-1084-8

ISSN

2472-6737

e-ISSN

2642-9381

Počet stran výsledku

10

Strana od-do

2322-2331

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Tucson

Datum konání akce

28. 2. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001481328900222