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

TL;DR

PP-Motion introduces a novel data-driven metric for evaluating human motion generation that combines physical feasibility and perceptual fidelity, using continuous annotations derived from minimal physical modifications.

Contribution

The paper presents a new physical labeling method and a combined perceptual-physical fidelity metric for more accurate evaluation of generated human motions.

Findings

PP-Motion aligns well with physical laws.

It correlates better with human perception than previous metrics.

Provides fine-grained, continuous annotations for motion fidelity.

Abstract

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.