Placing Human Animations into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframes

TL;DR

This paper introduces PAAK, a novel method for placing 3D human animations into scenes by learning interaction- and geometry-driven keyframes, improving interaction realism and placement accuracy.

Contribution

The paper proposes a new approach that identifies keyframes based on interaction importance, enhancing the placement of human animations in 3D scenes compared to prior methods.

Findings

PAAK outperforms previous methods in perceptual studies.

Human raters preferred PAAK over PROX 64.6% of the time.

PAAK was favored over POSA 61.5% of the time.

Abstract

We present a novel method for placing a 3D human animation into a 3D scene while maintaining any human-scene interactions in the animation. We use the notion of computing the most important meshes in the animation for the interaction with the scene, which we call "keyframes." These keyframes allow us to better optimize the placement of the animation into the scene such that interactions in the animations (standing, laying, sitting, etc.) match the affordances of the scene (e.g., standing on the floor or laying in a bed). We compare our method, which we call PAAK, with prior approaches, including POSA, PROX ground truth, and a motion synthesis method, and highlight the benefits of our method with a perceptual study. Human raters preferred our PAAK method over the PROX ground truth data 64.6\% of the time. Additionally, in direct comparisons, the raters preferred PAAK over competing methods including 61.5\% compared to POSA.