3D Surfel Map-Aided Visual Relocalization with Learned Descriptors

2021/04/08 by Haoyang Ye, Ye, Haoyang, Huaiyang Huang +7
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics (cs.RO) #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.2104.03856

openalex publication_date 2021/04/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we introduce a method for visual relocalization using the geometric information from a 3D surfel map. A visual database is first built by global indices from the 3D surfel map rendering, which provides associations between image points and 3D surfels. Surfel reprojection constraints are utilized to optimize the keyframe poses and map points in the visual database. A hierarchical camera relocalization algorithm then utilizes the visual database to estimate 6-DoF camera poses. Learned descriptors are further used to improve the performance in challenging cases. We present evaluation under real-world conditions and simulation to show the effectiveness and efficiency of our method, and make the final camera poses consistently well aligned with the 3D environment.

Citations

• EPnP: An Accurate O(n) Solution to the PnP Problem
• Random sample consensus

Related

• Map-free Visual Relocalization: Metric Pose Relative to a Single Image
• Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer
• Visual Localization in 3D Maps: Comparing Point Cloud, Mesh, and NeRF Representations
• Monocular Direct Sparse Localization in a Prior 3D Surfel Map
• D2S: Representing sparse descriptors and 3D coordinates for camera relocalization