Evaluating the Quality of a Synthesized Motion with the Fr\'echet Motion Distance
Antoine Maiorca, Youngwoo Yoon, Thierry Dutoit
TL;DR
This paper introduces the Fréchet Motion Distance, a novel metric for assessing the quality of synthesized motion sequences in animation and robotics.
Contribution
It proposes a new quantitative measure, the Fréchet Motion Distance, for evaluating the similarity between real and generated motion data.
Findings
The Fréchet Motion Distance correlates well with human judgments.
It outperforms existing metrics in distinguishing high-quality synthesized motions.
The method is computationally efficient and applicable to various motion datasets.
Abstract
Evaluating the Quality of a Synthesized Motion with the Fr\'echet Motion Distance
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Motion and Animation · Advanced Vision and Imaging · 3D Shape Modeling and Analysis