mlsanityData to 14 Oct 2026

KVN: Keypoints Voting Network with Differentiable RANSAC for Stereo Pose Estimation

arXiv 2307.11543 ↗First posted 21 Jul 2023cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Object pose estimation is a fundamental computer vision task exploited in several robotics and augmented reality applications. Many established approaches rely on predicting 2D-3D keypoint correspondences using RANSAC (Random sample consensus) and estimating the object pose using the PnP (Perspective-n-Point) algorithm. Being RANSAC non-differentiable, correspondences cannot be directly learned in an end-to-end fashion. In this paper, we address the stereo image-based object pose estimation problem by i) introducing a differentiable RANSAC layer into a well-known monocular pose estimation network; ii) exploiting an uncertainty-driven multi-view PnP solver which can fuse information from multiple views. We evaluate our approach on a challenging public stereo object pose estimation dataset and a custom-built dataset we call Transparent Tableware Dataset (TTD), yielding state-of-the-art results against other recent approaches. Furthermore, in our ablation study, we show that the differentiable RANSAC layer plays a significant role in the accuracy of the proposed method. We release with this paper the code of our method and the TTD dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 21 Jul 2023.

Builds on

33 of 51 references.

References · 33

  1. 2017Neural Discrete Representation Learningcited by 4,712
  2. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  3. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  4. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  5. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  6. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
  7. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  8. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  9. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  10. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  11. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  12. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
21 more
  1. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  2. 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
  3. 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
  4. 2019ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulationcited by 124
  5. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  6. 2019Single-Stage 6D Object Pose Estimationcited by 88
  7. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  8. 2019KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objectscited by 75
  9. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  10. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  11. 2020EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approachcited by 46
  12. 2021StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimationcited by 40
  13. 2020Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimizationcited by 38
  14. 20206D Object Pose Regression via Supervised Learning on Point Cloudscited by 33
  15. 2021Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overviewcited by 31
  16. 2022Generalized Differentiable RANSACcited by 30
  17. 2021Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Votingcited by 25
  18. 2022StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCScited by 18
  19. 2022YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint Regressioncited by 17
  20. 2022DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimationcited by 12
  21. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2

Built on by

Not cited yet.