mlsanityData to 14 Oct 2026

Continuous-Time SO(3) Forecasting with Savitzky--Golay Neural Controlled Differential Equations

arXiv 2506.06780 ↗First posted 7 Jun 2025cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Tracking and forecasting the rotation of objects is fundamental in computer vision and robotics, yet SO(3) extrapolation remains challenging as (1) sensor observations can be noisy and sparse, (2) motion patterns can be governed by complex dynamics, and (3) application settings can demand long-term forecasting. This work proposes modeling continuous-time rotational object dynamics on SO(3) using Neural Controlled Differential Equations guided by Savitzky-Golay paths. Unlike existing methods that rely on simplified motion assumptions, our method learns a general latent dynamical system of the underlying object trajectory while respecting the geometric structure of rotations. Experimental results on real-world data demonstrate compelling forecasting capabilities compared to existing approaches.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 22 of its 49 references that are in the map. First posted on arXiv 7 Jun 2025.

Builds on

22 of 49 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  3. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  4. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 537
  5. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
  6. 2019GRU-ODE-Bayes: Continuous modeling of sporadically-observed time seriescited by 231
  7. 2020An Analysis of SVD for Deep Rotation Estimationcited by 86
  8. 2021Deep Regression on Manifolds: A 3D Rotation Case Studycited by 67
  9. 2018The Double Sphere Camera Modelcited by 52
  10. 2016SE3-Nets: Learning Rigid Body Motion using Deep Neural Networkscited by 49
  11. 2024Learning with 3D rotations, a hitchhiker's guide to SO(3)cited by 42
  12. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
10 more
  1. 2024Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objectscited by 35
  2. 2021Projective Manifold Gradient Layer for Deep Rotation Regressioncited by 31
  3. 2020A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertaintycited by 30
  4. 2019Efficient Derivative Computation for Cumulative B-Splines on Lie Groupscited by 28
  5. 2019The Oxford Multimotion Dataset: Multiple SE(3) Motions with Ground Truthcited by 12
  6. 2024Continuous-Time State Estimation Methods in Robotics: A Surveycited by 10
  7. 2017Camera Pose Filtering with Local Regression Geodesics on the Riemannian Manifold of Dual Quaternionscited by 8
  8. 2022GraspARL: Dynamic Grasping via Adversarial Reinforcement Learningcited by 8
  9. 2023Learning to Predict 3D Rotational Dynamics from Images of a Rigid Body with Unknown Mass Distributioncited by 7
  10. 2018A White-Noise-On-Jerk Motion Prior for Continuous-Time Trajectory Estimation on SE(3)cited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Explicit and Effectively Symmetric Schemes for Neural SDEs on Lie Groupscited by 1
  2. 2026Learning Manifold and Ito Dynamics with Branched Neural Rough Differential Equationscited by 0