Multi-Resolution Haar Network: Enhancing human motion prediction via Haar transform

TL;DR

This paper introduces HaarMoDic, a novel network utilizing 2D Haar transform and multi-resolution analysis to improve 3D human motion prediction, significantly outperforming existing methods on the Human3.6M dataset.

Contribution

The paper proposes the Multi-Resolution Haar (MR-Haar) block within HaarMoDic, enabling simultaneous access to spatial and temporal information for better motion prediction.

Findings

HaarMoDic outperforms state-of-the-art methods on Human3.6M dataset.

The MR-Haar block effectively captures multi-resolution motion features.

Experimental results show improved accuracy across all testing intervals.

Abstract

The 3D human pose is vital for modern computer vision and computer graphics, and its prediction has drawn attention in recent years. 3D human pose prediction aims at forecasting a human's future motion from the previous sequence. Ignoring that the arbitrariness of human motion sequences has a firm origin in transition in both temporal and spatial axes limits the performance of state-of-the-art methods, leading them to struggle with making precise predictions on complex cases, e.g., arbitrarily posing or greeting. To alleviate this problem, a network called HaarMoDic is proposed in this paper, which utilizes the 2D Haar transform to project joints to higher resolution coordinates where the network can access spatial and temporal information simultaneously. An ablation study proves that the significant contributing module within the HaarModic Network is the Multi-Resolution Haar (MR-Haar) block. Instead of mining in one of two axes or extracting separately, the MR-Haar block projects whole motion sequences to a mixed-up coordinate in higher resolution with 2D Haar Transform, allowing the network to give scope to information from both axes in different resolutions. With the MR-Haar block, the HaarMoDic network can make predictions referring to a broader range of information. Experimental results demonstrate that HaarMoDic surpasses state-of-the-art methods in every testing interval on the Human3.6M dataset in the Mean Per Joint Position Error (MPJPE) metric.