CoPR: Towards Accurate Visual Localization With Continuous Place-descriptor Regression

Abstract

Visual Place Recognition (VPR) is an image-based localization method that estimates the camera location of a query image by retrieving the most similar reference image from a map of geo-tagged reference images. In this work, we look into two fundamental bottlenecks for its localization accuracy: reference map sparseness and viewpoint invariance. Firstly, the reference images for VPR are only available at sparse poses in a map, which enforces an upper bound on the maximum achievable localization accuracy through VPR. We therefore propose Continuous Place-descriptor Regression (CoPR) to densify the map and improve localization accuracy. We study various interpolation and extrapolation models to regress additional VPR feature descriptors from only the existing references. Secondly, we compare different feature encoders and show that CoPR presents value for all of them. We evaluate our models on three existing public datasets and report on average around 30% improvement in VPR-based localization accuracy using CoPR, on top of the 15% increase by using a viewpoint-variant loss for the feature encoder. The complementary relation between CoPR and Relative Pose Estimation is also discussed.

arXiv commentPublished in the IEEE Transactions on Robotics, April 2023

References in corpus (9)

• Gaussian Error Linear Units (GELUs)
• VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry
• Convolutional Neural Network-based Place Recognition
• Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis
• Where is your place, Visual Place Recognition?
• Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methods
• LENS: Localization enhanced by NeRF synthesis
• Generalized Contrastive Optimization of Siamese Networks for Place Recognition
• Geometrically Mappable Image Features