HUMOF: Human Motion Forecasting in Interactive Social Scenes

TL;DR

HUMOF introduces a hierarchical and coarse-to-fine reasoning approach for human motion forecasting in complex interactive scenes, leveraging spatial and frequency features to improve prediction accuracy.

Contribution

The paper presents a novel hierarchical interaction representation and a coarse-to-fine reasoning module that enhances motion prediction in complex social environments.

Findings

Achieves state-of-the-art results on four public datasets.

Effectively models human-human and human-environment interactions.

Utilizes spatial and frequency perspectives for improved reasoning.

Abstract

Complex scenes present significant challenges for predicting human behaviour due to the abundance of interaction information, such as human-human and humanenvironment interactions. These factors complicate the analysis and understanding of human behaviour, thereby increasing the uncertainty in forecasting human motions. Existing motion prediction methods thus struggle in these complex scenarios. In this paper, we propose an effective method for human motion forecasting in interactive scenes. To achieve a comprehensive representation of interactions, we design a hierarchical interaction feature representation so that high-level features capture the overall context of the interactions, while low-level features focus on fine-grained details. Besides, we propose a coarse-to-fine interaction reasoning module that leverages both spatial and frequency perspectives to efficiently utilize hierarchical features, thereby enhancing the accuracy of motion predictions. Our method achieves state-of-the-art performance across four public datasets. The source code will be available at https://github.com/scy639/HUMOF.