Breaking The Frame: Visual Place Recognition By Overlap Prediction

Abstract

Visual place recognition methods struggle with occlusions 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.

Stats

• citations3
• S2 citations—
• github stars43
• HF likes0
• heat score7.80
• arxiv keywei2024breaking

Code

• weitong8591/vop.git—

Related papers

• Regressing Transformers For Data-efficient Visual Place Recognition (2024)3.58
• Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70
• Spatio-semantic Convnet-based Visual Place Recognition (2019)10.21
• Predicting Visual Overlap Of Images Through Interpretable Non-metric Box Embeddings (2020)8.82
• Are Local Features All You Need For Cross-domain Visual Place Recognition? (2023)13.80
• VXP: Voxel-cross-pixel Large-scale Image-lidar Place Recognition (2024)5.24
• Fast, Compact And Highly Scalable Visual Place Recognition Through Sequence-based Matching Of Overloaded Representations (2020)9.41
• Eigenplaces: Training Viewpoint Robust Models For Visual Place Recognition (2023)15.46