mlsanityData to 7 Oct 2026

A Pose-only Solution to Visual Reconstruction and Navigation

arXiv 2103.01530 ↗First posted 2 Mar 2021cs.CV cs.ROcited by 20

Not on the map. Why?

Abstract (arXiv)

Visual navigation and three-dimensional (3D) scene reconstruction are essential for robotics to interact with the surrounding environment. Large-scale scenes and critical camera motions are great challenges facing the research community to achieve this goal. We raised a pose-only imaging geometry framework and algorithms that can help solve these challenges. The representation is a linear function of camera global translations, which allows for efficient and robust camera motion estimation. As a result, the spatial feature coordinates can be analytically reconstructed and do not require nonlinear optimization. Experiments demonstrate that the computational efficiency of recovering the scene and associated camera poses is significantly improved by 2-4 orders of magnitude. This solution might be promising to unlock real-time 3D visual computing in many forefront applications.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 5 of its 58 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

5 of 58 references.

References · 5

  1. 2014Robust Camera Location Estimation by Convex Programmingcited by 41
  2. 2019Baseline Desensitizing In Translation Averagingcited by 27
  3. 2016ShapeFit and ShapeKick for Robust, Scalable Structure from Motioncited by 16
  4. 2015Linear Global Translation Estimation with Feature Trackscited by 9
  5. 2018Equivalent Constraints for Two-View Geometry: Pose Solution/Pure Rotation Identification and 3D Reconstructioncited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 5; 2026: 6.

20 papers.

Sort:

  1. 2024Global Structure-from-Motion Revisitedcited by 215
  2. 2024GaussNav: Gaussian Splatting for Visual Navigationcited by 49
  3. 2025Light3R-SfM: Towards Feed-forward Structure-from-Motioncited by 47
  4. 2023RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereocited by 15
  5. 2023EC-SfM: Efficient Covisibility-based Structure-from-Motion for Both Sequential and Unordered Imagescited by 9
  6. 2025Regist3R: Incremental Registration with Stereo Foundation Modelcited by 9
  7. 2025JOG3R: Towards 3D-Consistent Video Generatorscited by 8
  8. 2024Six-Point Method for Multi-Camera Systems with Reduced Solution Spacecited by 7
  9. 2024Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Trackercited by 3
  10. 2024An Accurate and Real-time Relative Pose Estimation from Triple Point-line Images by Decoupling Rotation and Translationcited by 3
  11. 2024Linear Relative Pose Estimation Founded on Pose-only Imaging Geometrycited by 2
  12. 2024PO-MSCKF: An Efficient Visual-Inertial Odometry by Reconstructing the Multi-State Constrained Kalman Filter with the Pose-only Theorycited by 1
8 more
  1. 2026A Pose-only Geometric Constraint for Multi-Camera Pose Adjustmentcited by 1
  2. 2025MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motioncited by 0
  3. 2025Towards Rotation-only Imaging Geometry: Rotation Estimationcited by 0
  4. 2026POPL-KF: A Pose-Only Geometric Representation-Based Kalman Filter for Point-Line-Based Visual-Inertial Odometrycited by 0
  5. 2026HETA++: Global Structure-from-Motion with Hybrid Explicit Translation Averagingcited by 0
  6. 2026Triangulation-Free Bundle Adjustment with Graduated Non-Convexity for Camera Pose Refinement from Coarse Priorscited by 0
  7. 2026Robust Global Structure-from-Motion via View Graph Pruningcited by 0
  8. 2026Robust Structureless Monocular Visual Inertial Initialization Exploiting Line Features and Vanishing Pointscited by 0