Pith. sign in

REVIEW 4 cited by

Learning with 3D rotations, a hitchhiker's guide to SO(3)

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.11735 v2 pith:5RJVV5CK submitted 2024-04-17 cs.LG cs.CVcs.RO

A. René Geist , Jonas Frey , Mikel Zhobro , Anna Levina , Georg Martius This is my paper
classification cs.LGcs.CVcs.RO
keywords learningrepresentationsrotationguidemanyrepresentationrotationswhether
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Many settings in machine learning require the selection of a rotation representation. However, choosing a suitable representation from the many available options is challenging. This paper acts as a survey and guide through rotation representations. We walk through their properties that harm or benefit deep learning with gradient-based optimization. By consolidating insights from rotation-based learning, we provide a comprehensive overview of learning functions with rotation representations. We provide guidance on selecting representations based on whether rotations are in the model's input or output and whether the data primarily comprises small angles.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion

    cs.CV 2026-07 accept novelty 7.5 of 10

    A permutation-equivariant latent diffusion model treats skeleton connectivity as input, enabling the first kinematics-agnostic stochastic human motion predictor that generalizes zero-shot to unseen and partial skeletons.

  2. Revisiting Euler-Angle Regression with Kolmogorov-Arnold Networks

    cs.CV 2026-07 accept novelty 6.5 of 10

    Range-constrained Euler angles plus Kolmogorov-Arnold Networks outperform the standard MLP+6D pipeline on rotation regression for articulated systems.

  3. T-MASK: Temporal Masking for Probing Foundation Models across Camera Views in Driver Monitoring

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    T-MASK uses temporal token masking to improve cross-view driver activity recognition with foundation models, claiming gains of +1.23% over probing and +8.0% over PEFT on Drive&Act.

  4. Towards Human-level Intelligence via Human-like Whole-Body Manipulation

    cs.RO 2025-07 conditional novelty 6.0 of 10

    Astribot Suite integrates a human-like dual-arm mobile robot, VR whole-body teleoperation, and a diffusion-based whole-body policy, achieving 80% average success across six daily manipulation tasks.

Pith tools