mlsanityData to 7 Oct 2026

A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation

arXiv 2303.01743 ↗First posted 3 Mar 2023cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Estimating the 3DoF rotation from a single RGB image is an important yet challenging problem. Probabilistic rotation regression has raised more and more attention with the benefit of expressing uncertainty information along with the prediction. Though modeling noise using Gaussian-resembling Bingham distribution and matrix Fisher distribution is natural, they are shown to be sensitive to outliers for the nature of quadratic punishment to deviations. In this paper, we draw inspiration from multivariate Laplace distribution and propose a novel Rotation Laplace distribution on SO(3). Rotation Laplace distribution is robust to the disturbance of outliers and enforces much gradient to the low-error region, resulting in a better convergence. Our extensive experiments show that our proposed distribution achieves state-of-the-art performance for rotation regression tasks over both probabilistic and non-probabilistic baselines. Our project page is at https://pku-epic.github.io/RotationLaplace.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 31 of its 58 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

31 of 58 references.

References · 31

  1. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  3. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  4. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  5. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  6. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  7. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  8. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  9. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  10. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  11. 2018A micro Lie theory for state estimation in roboticscited by 117
  12. 2019Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Predictioncited by 96
19 more
  1. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 94
  2. 2020An Analysis of SVD for Deep Rotation Estimationcited by 85
  3. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  4. 2014Viewpoints and Keypointscited by 59
  5. 2018Deep Directional Statistics: Pose Estimation with Uncertainty Quantificationcited by 45
  6. 2020Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimationcited by 43
  7. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
  8. 2019Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spherescited by 37
  9. 2020Probabilistic orientation estimation with matrix Fisher distributionscited by 36
  10. 2021Projective Manifold Gradient Layer for Deep Rotation Regressioncited by 31
  11. 2018Deep-6DPose: Recovering 6D Object Pose from a Single RGB Imagecited by 26
  12. 2018A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Imagescited by 19
  13. 2020Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environmentscited by 19
  14. 2022FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filteringcited by 16
  15. 2017Bayesian Attitude Estimation with the Matrix Fisher Distribution on SO(3)cited by 11
  16. 2018Occlusion Resistant Object Rotation Regression from Point Cloud Segmentscited by 9
  17. 2020Towards Accurate Active Camera Localizationcited by 9
  18. 2022Maximum Likelihood Uncertainty Estimation: Robustness to Outlierscited by 6
  19. 2017A Generalised Directional Laplacian Distribution: Estimation, Mixture Models and Audio Source Separationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 0; 2026: 1.

9 papers.