mlsanityData to 7 Oct 2026

FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation

arXiv 2403.03221 ↗First posted 5 Mar 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Estimating relative camera poses between images has been a central problem in computer vision. Methods that find correspondences and solve for the fundamental matrix offer high precision in most cases. Conversely, methods predicting pose directly using neural networks are more robust to limited overlap and can infer absolute translation scale, but at the expense of reduced precision. We show how to combine the best of both methods; our approach yields results that are both precise and robust, while also accurately inferring translation scales. At the heart of our model lies a Transformer that (1) learns to balance between solved and learned pose estimations, and (2) provides a prior to guide a solver. A comprehensive analysis supports our design choices and demonstrates that our method adapts flexibly to various feature extractors and correspondence estimators, showing state-of-the-art performance in 6DoF pose estimation on Matterport3D, InteriorNet, StreetLearn, and Map-free Relocalization.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 58 of its 84 references that are in the map. First posted on arXiv 5 Mar 2024.

Builds on

58 of 84 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  5. 2021Vision Transformers for Dense Predictioncited by 1,789
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  7. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  8. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  9. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  11. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  12. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
38 more
  1. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  2. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  3. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  4. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  5. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  6. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
  7. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  8. 2022Deep Patch Visual Odometrycited by 186
  9. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  10. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  11. 2019MAGSAC++, a fast, reliable and accurate robust estimatorcited by 160
  12. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 146
  13. 2018MAGSAC: marginalizing sample consensuscited by 122
  14. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  15. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
  16. 2020TartanVO: A Generalizable Learning-based VOcited by 107
  17. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  18. 2018DS-SLAM: A Semantic Visual SLAM towards Dynamic Environmentscited by 90
  19. 2018StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Predictioncited by 88
  20. 2018InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Datasetcited by 87
  21. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  22. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  23. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  24. 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
  25. 2021Progressive Correspondence Pruning by Consensus Learningcited by 46
  26. 2019The StreetLearn Environment and Datasetcited by 42
  27. 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
  28. 2021Planar Surface Reconstruction from Sparse Viewscited by 40
  29. 2022The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTscited by 38
  30. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34
  31. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33
  32. 2023Doppelgangers: Learning to Disambiguate Images of Similar Structurescited by 32
  33. 2018RPNet: an End-to-End Network for Relative Camera Pose Estimationcited by 31
  34. 2022Adaptive Assignment for Geometry Aware Local Feature Matchingcited by 30
  35. 2022Generalized Differentiable RANSACcited by 30
  36. 2022PlaneFormers: From Sparse View Planes to 3D Reconstructioncited by 26
  37. 2018Beyond Gr"obner Bases: Basis Selection for Minimal Solverscited by 25
  38. 2015WxBS: Wide Baseline Stereo Generalizationscited by 23

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 4.

12 papers.

  1. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  2. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
  3. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
  4. 2025Scene-agnostic Pose Regression for Visual Localizationcited by 8
  5. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  6. 2024PEnG: Pose-Enhanced Geo-Localisationcited by 3
  7. 2025GeLoc3r: Enhancing Relative Camera Pose Regression with Geometric Consistency Regularizationcited by 2
  8. 2025iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversioncited by 0
  9. 2025Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Videocited by 0
  10. 2026TESO: Online Tracking of Essential Matrix by Stochastic Optimizationcited by 0
  11. 2026Agentic Relative Camera Pose Estimation via Learned Ranking and Verificationcited by 0
  12. 2026Supervising Sound Localization by In-the-wild Egomotioncited by 0