Yes, We CANN: Constrained Approximate Nearest Neighbors For Local Feature-based Visual Localization

Abstract

Large-scale visual localization systems continue to rely on 3D point clouds built from image collections using structure-from-motion. While the 3D points in these models are represented using local image features, directly matching a query image's local features against the point cloud is challenging due to the scale of the nearest-neighbor search problem. Many recent approaches to visual localization have thus proposed a hybrid method, where first a global (per image) embedding is used to retrieve a small subset of database images, and local features of the query are matched only against those. It seems to have become common belief that global embeddings are critical for said image-retrieval in visual localization, despite the significant downside of having to compute two feature types for each query image. In this paper, we take a step back from this assumption and propose Constrained Approximate Nearest Neighbors (CANN), a joint solution of k-nearest-neighbors across both the geomet

Stats

• citations5
• S2 citations—
• github stars37839
• HF likes0
• heat score14.99
• arxiv keyaiger2023yes

Related papers

• Leveraging Local And Global Descriptors In Parallel To Search Correspondences For Visual Localization (2020)8.82
• Sparse-to-dense Hypercolumn Matching For Long-term Visual Localization (2019)12.99
• Densernet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation (2020)15.62
• Leveraging Semantic Cues From Foundation Vision Models For Enhanced Local Feature Correspondence (2024)5.24
• Multiview Image-based Localization (2025)0.00
• Cross-view Image Matching For Geo-localization In Urban Environments (2017)17.16
• Are Local Features All You Need For Cross-domain Visual Place Recognition? (2023)13.80
• Self-localization From Images With Small Overlap (2016)8.35