REVIEW 5 cited by
Learning with 3D rotations, a hitchhiker's guide to SO(3)
Not yet reviewed by Pith; the record is open.
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
Learning with 3D rotations, a hitchhiker's guide to SO(3)
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.
Forward citations
Cited by 5 Pith papers
-
EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion
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.
-
Revisiting Euler-Angle Regression with Kolmogorov-Arnold Networks
Range-constrained Euler angles plus Kolmogorov-Arnold Networks outperform the standard MLP+6D pipeline on rotation regression for articulated systems.
-
Echo-POSED: Geometric Self-Distillation for Echocardiography Guidance
Echo-POSED learns an SO(3)×SO(3) pose representation via self-supervised equivariance to probe motion and invariance to cardiac phase from 2D slices of 3D echocardiography volumes, reporting 8.2° mean angular error in...
-
Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
RecGen achieves state-of-the-art 3D multi-object scene reconstruction from sparse RGB-D views by combining compositional synthetic scene generation with strong 3D shape priors, outperforming SAM3D by 30%+ in shape qua...
-
ELMP: Efficient Learning for Motion Planning via Analytical Policy Gradients
ELMP performs data-efficient self-supervised adaptation of neural motion planners via analytical policy gradients and point-cloud tool encoding, raising success from 57.3% zero-shot to 89.8% in unseen environments.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.