PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Sihan, Wang, Zixuan, Luan, Tianyu, Jia, Jia, Zhu, Wentao, Luo, Jiebo, Yuan, Junsong, Xi, Nan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914337899151360
author Zhao, Sihan
Wang, Zixuan
Luan, Tianyu
Jia, Jia
Zhu, Wentao
Luo, Jiebo
Yuan, Junsong
Xi, Nan
author_facet Zhao, Sihan
Wang, Zixuan
Luan, Tianyu
Jia, Jia
Zhu, Wentao
Luo, Jiebo
Yuan, Junsong
Xi, Nan
contents Human motion generation has found widespread applications in AR/VR, film, sports, and medical rehabilitation, offering a cost-effective alternative to traditional motion capture systems. However, evaluating the fidelity of such generated motions is a crucial, multifaceted task. Although previous approaches have attempted at motion fidelity evaluation using human perception or physical constraints, there remains an inherent gap between human-perceived fidelity and physical feasibility. Moreover, the subjective and coarse binary labeling of human perception further undermines the development of a robust data-driven metric. We address these issues by introducing a physical labeling method. This method evaluates motion fidelity by calculating the minimum modifications needed for a motion to align with physical laws. With this approach, we are able to produce fine-grained, continuous physical alignment annotations that serve as objective ground truth. With these annotations, we propose PP-Motion, a novel data-driven metric to evaluate both physical and perceptual fidelity of human motion. To effectively capture underlying physical priors, we employ Pearson's correlation loss for the training of our metric. Additionally, by incorporating a human-based perceptual fidelity loss, our metric can capture fidelity that simultaneously considers both human perception and physical alignment. Experimental results demonstrate that our metric, PP-Motion, not only aligns with physical laws but also aligns better with human perception of motion fidelity than previous work.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation
Zhao, Sihan
Wang, Zixuan
Luan, Tianyu
Jia, Jia
Zhu, Wentao
Luo, Jiebo
Yuan, Junsong
Xi, Nan
Computer Vision and Pattern Recognition
Multimedia
Human motion generation has found widespread applications in AR/VR, film, sports, and medical rehabilitation, offering a cost-effective alternative to traditional motion capture systems. However, evaluating the fidelity of such generated motions is a crucial, multifaceted task. Although previous approaches have attempted at motion fidelity evaluation using human perception or physical constraints, there remains an inherent gap between human-perceived fidelity and physical feasibility. Moreover, the subjective and coarse binary labeling of human perception further undermines the development of a robust data-driven metric. We address these issues by introducing a physical labeling method. This method evaluates motion fidelity by calculating the minimum modifications needed for a motion to align with physical laws. With this approach, we are able to produce fine-grained, continuous physical alignment annotations that serve as objective ground truth. With these annotations, we propose PP-Motion, a novel data-driven metric to evaluate both physical and perceptual fidelity of human motion. To effectively capture underlying physical priors, we employ Pearson's correlation loss for the training of our metric. Additionally, by incorporating a human-based perceptual fidelity loss, our metric can capture fidelity that simultaneously considers both human perception and physical alignment. Experimental results demonstrate that our metric, PP-Motion, not only aligns with physical laws but also aligns better with human perception of motion fidelity than previous work.
title PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2508.08179