Pith. sign in

REVIEW 2 cited by

EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning

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

arxiv 2303.10876 v2 pith:7YMHOYVF submitted 2023-03-20 cs.CV cs.MA

classification cs.CVcs.MA
keywords motionpredictionequivariantfeatureinteractioninvariantproposereasoning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning to predict agent motions with relationship reasoning is important for many applications. In motion prediction tasks, maintaining motion equivariance under Euclidean geometric transformations and invariance of agent interaction is a critical and fundamental principle. However, such equivariance and invariance properties are overlooked by most existing methods. To fill this gap, we propose EqMotion, an efficient equivariant motion prediction model with invariant interaction reasoning. To achieve motion equivariance, we propose an equivariant geometric feature learning module to learn a Euclidean transformable feature through dedicated designs of equivariant operations. To reason agent's interactions, we propose an invariant interaction reasoning module to achieve a more stable interaction modeling. To further promote more comprehensive motion features, we propose an invariant pattern feature learning module to learn an invariant pattern feature, which cooperates with the equivariant geometric feature to enhance network expressiveness. We conduct experiments for the proposed model on four distinct scenarios: particle dynamics, molecule dynamics, human skeleton motion prediction and pedestrian trajectory prediction. Experimental results show that our method is not only generally applicable, but also achieves state-of-the-art prediction performances on all the four tasks, improving by 24.0/30.1/8.6/9.2%. Code is available at https://github.com/MediaBrain-SJTU/EqMotion.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulation

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A flow-matching model that builds its starting noise from random walks matched to the observed motion produces more accurate trajectory predictions with only 5 integration steps.

  2. UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction

    cs.RO 2025-05 conditional novelty 5.0 of 10

    UPTor couples 3D pose dynamics and trajectory prediction into one non-autoregressive transformer using a translation and rotation normalization, and adds the DARKO navigation dataset.

Pith tools