mlsanityData to 14 Oct 2026

Coarse-to-Fine Multi-Scene Pose Regression with Transformers

arXiv 2308.11783 ↗First posted 22 Aug 2023cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Absolute camera pose regressors estimate the position and orientation of a camera given the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron (MLP) head is trained using images and pose labels to embed a single reference scene at a time. Recently, this scheme was extended to learn multiple scenes by replacing the MLP head with a set of fully connected layers. In this work, we propose to learn multi-scene absolute camera pose regression with Transformers, where encoders are used to aggregate activation maps with self-attention and decoders transform latent features and scenes encoding into pose predictions. This allows our model to focus on general features that are informative for localization, while embedding multiple scenes in parallel. We extend our previous MS-Transformer approach citeshavit2021learning by introducing a mixed classification-regression architecture that improves the localization accuracy. Our method is evaluated on commonly benchmark indoor and outdoor datasets and has been shown to exceed both multi-scene and state-of-the-art single-scene absolute pose regressors.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 33 of its 56 references that are in the map. First posted on arXiv 22 Aug 2023.

Builds on

33 of 56 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2016Layer Normalizationcited by 5,669
  8. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  9. 2020Rethinking Attention with Performerscited by 1,601
  10. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  11. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  12. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
21 more
  1. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  2. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  3. 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
  4. 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
  5. 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
  6. 2016Image-based localization using LSTMs for structured feature correlationcited by 136
  7. 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 134
  8. 2019Rank consistent ordinal regression for neural networks with application to age estimationcited by 133
  9. 2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
  10. 2019AtLoc: Attention Guided Camera Localizationcited by 92
  11. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  12. 2019Expert Sample Consensus Applied to Camera Re-Localizationcited by 70
  13. 2018VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometrycited by 61
  14. 2019To Learn or Not to Learn: Visual Localization from Essential Matricescited by 61
  15. 2018Deep Auxiliary Learning for Visual Localization and Odometrycited by 59
  16. 2021Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervisioncited by 37
  17. 2019Introduction to Camera Pose Estimation with Deep Learningcited by 25
  18. 2019Local Supports Global: Deep Camera Relocalization with Sequence Enhancementcited by 25
  19. 2018Improved Visual Relocalization by Discovering Anchor Pointscited by 16
  20. 2020Do We Really Need Scene-specific Pose Encoders?cited by 10
  21. 2021Universally Rank Consistent Ordinal Regression in Neural Networkscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 2; 2026: 3.

11 papers.

  1. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 82
  2. 2024Differentiable Product Quantization for Memory Efficient Camera Relocalizationcited by 9
  3. 2024RDPN6D: Residual-based Dense Point-wise Network for 6Dof Object Pose Estimation Based on RGB-D Imagescited by 5
  4. 2025Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformercited by 5
  5. 2024Activating Self-Attention for Multi-Scene Absolute Pose Regressioncited by 2
  6. 2024ConDo: Continual Domain Expansion for Absolute Pose Regressioncited by 2
  7. 2025MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalizationcited by 1
  8. 2024MambaLoc: Efficient Camera Localisation via State Space Modelcited by 0
  9. 2026Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localizationcited by 0
  10. 2026Learning 1-Bit LiDAR-based Localization with Auxiliary Objectivecited by 0
  11. 2026LightLoc++: Sensor-Robust Representation Learning for Efficient Outdoor LiDAR Localizationcited by 0