mlsanityData to 7 Oct 2026

Calibrated and Partially Calibrated Semi-Generalized Homographies

arXiv 2103.06535 ↗First posted 11 Mar 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose the first minimal solutions for estimating the semi-generalized homography given a perspective and a generalized camera. The proposed solvers use five 2D-2D image point correspondences induced by a scene plane. One of them assumes the perspective camera to be fully calibrated, while the other solver estimates the unknown focal length together with the absolute pose parameters. This setup is particularly important in structure-from-motion and image-based localization pipelines, where a new camera is localized in each step with respect to a set of known cameras and 2D-3D correspondences might not be available. As a consequence of a clever parametrization and the elimination ideal method, our approach only needs to solve a univariate polynomial of degree five or three. The proposed solvers are stable and efficient as demonstrated by a number of synthetic and real-world experiments.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 14 of its 59 references that are in the map. First posted on arXiv 11 Mar 2021.

Builds on

14 of 59 references.

References · 14

  1. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  2. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  3. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
  4. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  5. 2017Graph-Cut RANSACcited by 133
  6. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  7. 2019Expert Sample Consensus Applied to Camera Re-Localizationcited by 70
  8. 2019To Learn or Not to Learn: Visual Localization from Essential Matricescited by 61
  9. 2019Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithmcited by 43
  10. 2019Why Having 10,000 Parameters in Your Camera Model is Better Than Twelvecited by 43
  11. 2020Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenescited by 31
  12. 2017A clever elimination strategy for efficient minimal solverscited by 17
2 more
  1. 2018Five-point Fundamental Matrix Estimation for Uncalibrated Camerascited by 11
  2. 2019Homography from two orientation- and scale-covariant featurescited by 8

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 4; 2025: 3.

12 papers.

  1. 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
  2. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  3. 2023Visual Localization using Imperfect 3D Models from the Internetcited by 20
  4. 2024"Where am I?" Scene Retrieval with Languagecited by 15
  5. 2025Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localizationcited by 10
  6. 2025A Guide to Structureless Visual Localizationcited by 9
  7. 2021Finding Geometric Models by Clustering in the Consensus Spacecited by 8
  8. 2023Lazy Visual Localization via Motion Averagingcited by 8
  9. 2024Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinementcited by 5
  10. 2025A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Featurescited by 4
  11. 2024Combining Absolute and Semi-Generalized Relative Poses for Visual Localizationcited by 3
  12. 2022Partially calibrated semi-generalized pose from hybrid point correspondencescited by 2