mlsanityData to 14 Oct 2026

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

arXiv 2304.07426 ↗First posted 14 Apr 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 61 references that are in the map. First posted on arXiv 14 Apr 2023.

Builds on

37 of 61 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  5. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  6. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  7. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  8. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  9. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
  10. 2013OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networkscited by 224
  11. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  12. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
25 more
  1. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  2. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 185
  3. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  4. 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
  5. 2016Image-based localization using LSTMs for structured feature correlationcited by 136
  6. 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 134
  7. 2016End-to-end Learning of Deep Visual Representations for Image Retrievalcited by 122
  8. 2021LENS: Localization enhanced by NeRF synthesiscited by 117
  9. 2020VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Changecited by 101
  10. 2017Deep Learning Features at Scale for Visual Place Recognitioncited by 96
  11. 2021Where is your place, Visual Place Recognition?cited by 82
  12. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  13. 2015On the Performance of ConvNet Features for Place Recognitioncited by 72
  14. 2019Expert Sample Consensus Applied to Camera Re-Localizationcited by 70
  15. 2017Image-based Localization using Hourglass Networkscited by 63
  16. 2018VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometrycited by 61
  17. 2018Deep Auxiliary Learning for Visual Localization and Odometrycited by 59
  18. 2017VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalizationcited by 58
  19. 2019Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methodscited by 38
  20. 2021Viewpoint Invariant Dense Matching for Visual Geolocalizationcited by 36
  21. 2014Convolutional Neural Network-based Place Recognitioncited by 32
  22. 2021Generalized Contrastive Optimization of Siamese Networks for Place Recognitioncited by 27
  23. 2020Hierarchical Multi-Process Fusion for Visual Place Recognitioncited by 24
  24. 2018Improved Visual Relocalization by Discovering Anchor Pointscited by 16
  25. 2020Geometrically Mappable Image Featurescited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024On the Estimation of Image-matching Uncertainty in Visual Place Recognitioncited by 16
  2. 2026MAG-VLAQ: Multi-modal Aerial-Ground Query Aggregation for Cross-View Place Recognitioncited by 0