mlsanityData to 14 Oct 2026

Camera Pose Auto-Encoders for Improving Pose Regression

arXiv 2207.05530 ↗First posted 12 Jul 2022cs.CV cs.AIcited by 28

Not on the map. Why?

Abstract (arXiv)

Absolute pose regressor (APR) networks are trained to estimate the pose of the camera given a captured image. They compute latent image representations from which the camera position and orientation are regressed. APRs provide a different tradeoff between localization accuracy, runtime, and memory, compared to structure-based localization schemes that provide state-of-the-art accuracy. In this work, we introduce Camera Pose Auto-Encoders (PAEs), multilayer perceptrons that are trained via a Teacher-Student approach to encode camera poses using APRs as their teachers. We show that the resulting latent pose representations can closely reproduce APR performance and demonstrate their effectiveness for related tasks. Specifically, we propose a light-weight test-time optimization in which the closest train poses are encoded and used to refine camera position estimation. This procedure achieves a new state-of-the-art position accuracy for APRs, on both the CambridgeLandmarks and 7Scenes benchmarks. We also show that train images can be reconstructed from the learned pose encoding, paving the way for integrating visual information from the train set at a low memory cost. Our code and pre-trained models are available at https://github.com/yolish/camera-pose-auto-encoders.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 12 Jul 2022.

Builds on

30 of 48 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  7. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  8. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  9. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
  10. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  11. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  12. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
18 more
  1. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  2. 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
  3. 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
  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. 2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
  8. 2019AtLoc: Attention Guided Camera Localizationcited by 92
  9. 2017Image-based Localization using Hourglass Networkscited by 63
  10. 2018VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometrycited by 61
  11. 2019To Learn or Not to Learn: Visual Localization from Essential Matricescited by 61
  12. 2018Deep Auxiliary Learning for Visual Localization and Odometrycited by 59
  13. 2017On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisationcited by 38
  14. 2021Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervisioncited by 37
  15. 2019Introduction to Camera Pose Estimation with Deep Learningcited by 25
  16. 2018Improved Visual Relocalization by Discovering Anchor Pointscited by 16
  17. 2020Efficient Scene Compression for Visual-based Localizationcited by 12
  18. 2020Do We Really Need Scene-specific Pose Encoders?cited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 5; 2024: 11; 2025: 7; 2026: 3.

28 papers.

Sort:

  1. 2024Map-Relative Pose Regression for Visual Re-Localizationcited by 42
  2. 2023Neural Refinement for Absolute Pose Regression with Feature Synthesiscited by 37
  3. 2023HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformercited by 26
  4. 2025From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splattingcited by 14
  5. 2024Learning Neural Volumetric Pose Features for Camera Localizationcited by 11
  6. 2022Improving Feature-based Visual Localization by Geometry-Aided Matchingcited by 8
  7. 2023Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environmentscited by 5
  8. 2024Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Informationcited by 4
  9. 2024Adversarial Exploitation of Data Diversity Improves Visual Localizationcited by 4
  10. 2023Learning to Localize in Unseen Scenes with Relative Pose Regressorscited by 3
  11. 2024EffLoc: Lightweight Vision Transformer for Efficient 6-DOF Camera Relocalizationcited by 3
  12. 2024NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired Peoplecited by 2
16 more
  1. 2024Activating Self-Attention for Multi-Scene Absolute Pose Regressioncited by 2
  2. 2025ActLoc: Learning to Localize on the Move via Active Viewpoint Selectioncited by 2
  3. 2022A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objectivecited by 1
  4. 2024VRS-NeRF: Visual Relocalization with Sparse Neural Radiance Fieldcited by 1
  5. 2024FaVoR: Features via Voxel Rendering for Camera Relocalizationcited by 1
  6. 2025GRLoc: Geometric Representation Regression for Visual Localizationcited by 1
  7. 2023Estimating Extreme 3D Image Rotation with Transformer Cross-Attentioncited by 0
  8. 2024PRAM: Place Recognition Anywhere Model for Efficient Visual Localizationcited by 0
  9. 2024PoseINN: Realtime Visual-based Pose Regression and Localization with Invertible Neural Networkscited by 0
  10. 2025HAL-NeRF: High Accuracy Localization Leveraging Neural Radiance Fieldscited by 0
  11. 2025APR-Transformer: Initial Pose Estimation for Localization in Complex Environments through Absolute Pose Regressioncited by 0
  12. 2025Robust Visual Localization via Semantic-Guided Multi-Scale Transformercited by 0
  13. 2025Relative Pose Regression with Pose Auto-Encoders: Enhancing Accuracy and Data Efficiency for Retail Applicationscited by 0
  14. 2026Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian Splattingcited by 0
  15. 2026PoseCompass: Intelligent Synthetic Pose Selection for Visual Localizationcited by 0
  16. 2026AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Object Pose Transformer: Unifying Unseen Object Pose Estimation
  2. 2026LA-Pose: Latent Action Pretraining Meets Pose Estimation
  3. 2025Scene-agnostic Pose Regression for Visual Localization
  4. 2026Agentic Relative Camera Pose Estimation via Learned Ranking and Verification
  5. 2023Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
  6. 2023QPoser: Quantized Explicit Pose Prior Modeling for Controllable Pose Generation
  7. 2026Improved Baselines with Representation Autoencoders
  8. 2024Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction