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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bastian, Lennart, Rashed, Mohammad, Navab, Nassir, Birdal, Tolga
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916784131538944
author Bastian, Lennart
Rashed, Mohammad
Navab, Nassir
Birdal, Tolga
author_facet Bastian, Lennart
Rashed, Mohammad
Navab, Nassir
Birdal, Tolga
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06780
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continuous-Time SO(3) Forecasting with Savitzky--Golay Neural Controlled Differential Equations
Bastian, Lennart
Rashed, Mohammad
Navab, Nassir
Birdal, Tolga
Computer Vision and Pattern Recognition
Machine Learning
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.
title Continuous-Time SO(3) Forecasting with Savitzky--Golay Neural Controlled Differential Equations
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2506.06780