Scene-aware Human Motion Forecasting via Mutual Distance Prediction

TL;DR

This paper introduces a novel scene-aware human motion forecasting method that models human-scene interactions through mutual distances, improving the accuracy of future human motion predictions in complex environments.

Contribution

The paper proposes a mutual distance-based approach combined with a global scene representation to better constrain and predict human motion considering scene interactions.

Findings

Outperforms state-of-the-art methods on synthetic and real datasets.

Effectively models both local and global human-scene interactions.

Ensures coherence between predicted human motion and scene geometry.

Abstract

In this paper, we tackle the problem of scene-aware 3D human motion forecasting. A key challenge of this task is to predict future human motions that are consistent with the scene by modeling the human-scene interactions. While recent works have demonstrated that explicit constraints on human-scene interactions can prevent the occurrence of ghost motion, they only provide constraints on partial human motion e.g., the global motion of the human or a few joints contacting the scene, leaving the rest of the motion unconstrained. To address this limitation, we propose to model the human-scene interaction with the mutual distance between the human body and the scene. Such mutual distances constrain both the local and global human motion, resulting in a whole-body motion constrained prediction. In particular, mutual distance constraints consist of two components, the signed distance of each vertex on the human mesh to the scene surface and the distance of basis scene points to the human mesh. We further introduce a global scene representation learned from a signed distance function (SDF) volume to ensure coherence between the global scene representation and the explicit constraint from the mutual distance. We develop a pipeline with two sequential steps: predicting the future mutual distances first, followed by forecasting future human motion. During training, we explicitly encourage consistency between predicted poses and mutual distances. Extensive evaluations on the existing synthetic and real datasets demonstrate that our approach consistently outperforms the state-of-the-art methods.