mlsanityData to 7 Oct 2026

SRPose: Two-view Relative Pose Estimation with Sparse Keypoints

arXiv 2407.08199 ↗First posted 11 Jul 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Two-view pose estimation is essential for map-free visual relocalization and object pose tracking tasks. However, traditional matching methods suffer from time-consuming robust estimators, while deep learning-based pose regressors only cater to camera-to-world pose estimation, lacking generalizability to different image sizes and camera intrinsics. In this paper, we propose SRPose, a sparse keypoint-based framework for two-view relative pose estimation in camera-to-world and object-to-camera scenarios. SRPose consists of a sparse keypoint detector, an intrinsic-calibration position encoder, and promptable prior knowledge-guided attention layers. Given two RGB images of a fixed scene or a moving object, SRPose estimates the relative camera or 6D object pose transformation. Extensive experiments demonstrate that SRPose achieves competitive or superior performance compared to state-of-the-art methods in terms of accuracy and speed, showing generalizability to both scenarios. It is robust to different image sizes and camera intrinsics, and can be deployed with low computing resources.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 62 of its 78 references that are in the map. First posted on arXiv 11 Jul 2024.

Builds on

62 of 78 references.

References · 62

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2023Segment Anythingcited by 8,158
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  7. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  8. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  9. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  10. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  11. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  12. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
38 more
  1. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  2. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  3. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 324
  4. 2020DISK: Learning local features with policy gradientcited by 310
  5. 2016LIFT: Learned Invariant Feature Transformcited by 305
  6. 2023RoMa: Robust Dense Feature Matchingcited by 296
  7. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  8. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  9. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  10. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
  11. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 146
  12. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 144
  13. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 129
  14. 2022QuadTree Attention for Vision Transformerscited by 129
  15. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  16. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  17. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 120
  18. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
  19. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
  20. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  21. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  22. 2020Dual-Resolution Correspondence Networkscited by 90
  23. 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87
  24. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  25. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  26. 2021ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extractioncited by 77
  27. 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
  28. 2019To Learn or Not to Learn: Visual Localization from Essential Matricescited by 61
  29. 2022Zero-Shot Category-Level Object Pose Estimationcited by 57
  30. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  31. 2017Relative Camera Pose Estimation Using Convolutional Neural Networkscited by 47
  32. 2019GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNscited by 47
  33. 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
  34. 2021Planar Surface Reconstruction from Sparse Viewscited by 40
  35. 2019Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Taskcited by 39
  36. 2017Toward Geometric Deep SLAMcited by 38
  37. 2022The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTscited by 38
  38. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2025RUBIK: A Structured Benchmark for Image Matching across Geometric Challengescited by 8
  2. 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
  3. 2026FSMC-Pose: Frequency and Spatial Fusion with Multiscale Self-calibration for Cattle Mounting Pose Estimationcited by 0
  4. 2026IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1cited by 0
  5. 2026StereoGeo: an end-to-end stereo camera calibration methodcited by 0