mlsanityData to 14 Oct 2026

Level Set-Based Camera Pose Estimation From Multiple 2D/3D Ellipse-Ellipsoid Correspondences

arXiv 2207.07953 ↗First posted 16 Jul 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose an object-based camera pose estimation from a single RGB image and a pre-built map of objects, represented with ellipsoidal models. We show that contrary to point correspondences, the definition of a cost function characterizing the projection of a 3D object onto a 2D object detection is not straightforward. We develop an ellipse-ellipse cost based on level sets sampling, demonstrate its nice properties for handling partially visible objects and compare its performance with other common metrics. Finally, we show that the use of a predictive uncertainty on the detected ellipses allows a fair weighting of the contribution of the correspondences which improves the computed pose. The code is released at https://gitlab.inria.fr/tangram/level-set-based-camera-pose-estimation.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 16 Jul 2022.

Builds on

24 of 40 references.

References · 24

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  7. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  8. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  9. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  10. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  11. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  12. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
12 more
  1. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  2. 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
  3. 2016Image-based localization using LSTMs for structured feature correlationcited by 136
  4. 2018CubeSLAM: Monocular 3D Object SLAMcited by 102
  5. 2018QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAMcited by 86
  6. 2018Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Drivingcited by 26
  7. 2018Structure Aware SLAM using Quadrics and Planescited by 17
  8. 2019Deep-SLAM++: Object-level RGBD SLAM based on class-specific deep shape priorscited by 8
  9. 2020Ellipse Detection and Localization with Applications to Knots in Sawn Lumber Imagescited by 8
  10. 2018Scene Coordinate and Correspondence Learning for Image-Based Localizationcited by 7
  11. 20213D-Aware Ellipse Prediction for Object-Based Camera Pose Estimationcited by 6
  12. 2020Ellipse Regression with Predicted Uncertainties for Accurate Multi-View 3D Object Estimationcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2024CLIP-Clique: Graph-based Correspondence Matching Augmented by Vision Language Models for Object-based Global Localizationcited by 3
  2. 20233D-Aware Object Localization using Gaussian Implicit Occupancy Functioncited by 2
  3. 2023UniQuadric: A SLAM Backend for Unknown Rigid Object 3D Tracking and Light-Weight Modelingcited by 1