mlsanityData to 7 Oct 2026

Learning Neural Volumetric Pose Features for Camera Localization

arXiv 2403.12800 ↗First posted 19 Mar 2024cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

We introduce a novel neural volumetric pose feature, termed PoseMap, designed to enhance camera localization by encapsulating the information between images and the associated camera poses. Our framework leverages an Absolute Pose Regression (APR) architecture, together with an augmented NeRF module. This integration not only facilitates the generation of novel views to enrich the training dataset but also enables the learning of effective pose features. Additionally, we extend our architecture for self-supervised online alignment, allowing our method to be used and fine-tuned for unlabelled images within a unified framework. Experiments demonstrate that our method achieves 14.28% and 20.51% performance gain on average in indoor and outdoor benchmark scenes, outperforming existing APR methods with state-of-the-art accuracy.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

25 of 44 references.

References · 25

  1. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  2. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  3. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  4. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
  5. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  6. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  7. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  8. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  9. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  10. 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
  11. 2016Image-based localization using LSTMs for structured feature correlationcited by 136
  12. 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 133
13 more
  1. 2021LENS: Localization enhanced by NeRF synthesiscited by 116
  2. 2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
  3. 2022DFNet: Enhance Absolute Pose Regression with Direct Feature Matchingcited by 82
  4. 2017Image-based Localization using Hourglass Networkscited by 63
  5. 2018VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometrycited by 61
  6. 2021Direct-PoseNet: Absolute Pose Regression with Photometric Consistencycited by 61
  7. 2018Deep Auxiliary Learning for Visual Localization and Odometrycited by 59
  8. 2023CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representationcited by 45
  9. 2022Camera Pose Auto-Encoders for Improving Pose Regressioncited by 28
  10. 2024HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisationcited by 16
  11. 2021Paying Attention to Activation Maps in Camera Pose Regressioncited by 10
  12. 2023Lazy Visual Localization via Motion Averagingcited by 8
  13. 2023PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 4.

11 papers.

  1. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
  2. 2024GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splattingcited by 31
  3. 2025Scene-agnostic Pose Regression for Visual Localizationcited by 8
  4. 2025Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformercited by 5
  5. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  6. 2024Adversarial Exploitation of Data Diversity Improves Visual Localizationcited by 4
  7. 2025GRLoc: Geometric Representation Regression for Visual Localizationcited by 1
  8. 2026Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertaintycited by 1
  9. 2025HAL-NeRF: High Accuracy Localization Leveraging Neural Radiance Fieldscited by 0
  10. 2026L3:Scene-agnostic Visual Localization in the Wildcited by 0
  11. 2026InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Datasetcited by 0