mlsanityData to 7 Oct 2026

Probabilistic orientation estimation with matrix Fisher distributions

arXiv 2006.09740 ↗First posted 17 Jun 2020cs.CV cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

This paper focuses on estimating probability distributions over the set of 3D rotations (SO(3)) using deep neural networks. Learning to regress models to the set of rotations is inherently difficult due to differences in topology between ℝN and SO(3). We overcome this issue by using a neural network to output the parameters for a matrix Fisher distribution since these parameters are homeomorphic to ℝ9. By using a negative log likelihood loss for this distribution we get a loss which is convex with respect to the network outputs. By optimizing this loss we improve state-of-the-art on several challenging applicable datasets, namely Pascal3D+, ModelNet10-SO(3) and UPNA head pose.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 5; 2023: 9; 2024: 5; 2025: 7; 2026: 4.

36 papers.

Sort:

By area:

  1. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  2. 2021Deep Regression on Manifolds: A 3D Rotation Case Studycited by 67
  3. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  4. 2021Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wildcited by 48
  5. 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
  6. 2021Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wildcited by 40
  7. 2023Equivariant Adaptation of Large Pretrained Modelscited by 40
  8. 2023HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimationcited by 23
  9. 2023Image to Sphere: Learning Equivariant Features for Efficient Pose Predictioncited by 17
  10. 2023XVO: Generalized Visual Odometry via Cross-Modal Self-Trainingcited by 17
  11. 2022FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filteringcited by 16
  12. 2023Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modelingcited by 14
24 more
  1. 2024SimpleEgo: Predicting Probabilistic Body Pose from Egocentric Camerascited by 12
  2. 2023A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimationcited by 9
  3. 2022Ki-Pode: Keypoint-based Implicit Pose Distribution Estimation of Rigid Objectscited by 7
  4. 2023Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distributioncited by 5
  5. 2023Unified framework for diffusion generative models in SO(3): applications in computer vision and astrophysicscited by 5
  6. 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Predictioncited by 4
  7. 2025ZeroVO: Visual Odometry with Minimal Assumptionscited by 4
  8. 2025Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflowcited by 4
  9. 2021Probabilistic Regression with Huber Distributionscited by 2
  10. 2022Stable Object Reorientation using Contact Plane Registrationcited by 2
  11. 2022Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labelscited by 2
  12. 2024Semi-Supervised Unconstrained Head Pose Estimation in the Wildcited by 2
  13. 2025Are Euler angles a useful rotation parameterisation for pose estimation with Normalizing Flows?cited by 2
  14. 2024MOSS: Motion-based 3D Clothed Human Synthesis from Monocular Videocited by 1
  15. 2025Riemannian Neural Geodesic Interpolantcited by 1
  16. 2025RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalizationcited by 1
  17. 2025MimiCAT: Mimic with Correspondence-Aware Cascade-Transformer for Category-Free 3D Pose Transfercited by 1
  18. 2023Estimating Extreme 3D Image Rotation with Transformer Cross-Attentioncited by 0
  19. 2024On the power of data augmentation for head pose estimationcited by 0
  20. 2025Matching the Optimal Denoiser in Point Cloud Diffusion with (Improved) Rotational Alignmentcited by 0
  21. 2026OpenVO: Open-World Visual Odometry with Temporal Dynamics Awarenesscited by 0
  22. 2026HACMatch Semi-Supervised Rotation Regression with Hardness-Aware Curriculum Pseudo Labelingcited by 0
  23. 2026Coordinate Singularities Break Conformal Coverage for Gaze and Head Posecited by 0
  24. 2026Predicting build orientation for SLM dental parts: a comparison of rotation representations and direct vector regressioncited by 0