Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction

by   Maosen Li, et al.

Graph convolutional network based methods that model the body-joints' relations, have recently shown great promise in 3D skeleton-based human motion prediction. However, these methods have two critical issues: first, deep graph convolutions filter features within only limited graph spectrums, losing sufficient information in the full band; second, using a single graph to model the whole body underestimates the diverse patterns on various body-parts. To address the first issue, we propose adaptive graph scattering, which leverages multiple trainable band-pass graph filters to decompose pose features into richer graph spectrum bands. To address the second issue, body-parts are modeled separately to learn diverse dynamics, which enables finer feature extraction along the spatial dimensions. Integrating the above two designs, we propose a novel skeleton-parted graph scattering network (SPGSN). The cores of the model are cascaded multi-part graph scattering blocks (MPGSBs), building adaptive graph scattering on diverse body-parts, as well as fusing the decomposed features based on the inferred spectrum importance and body-part interactions. Extensive experiments have shown that SPGSN outperforms state-of-the-art methods by remarkable margins of 13.8 of 3D mean per joint position error (MPJPE) on Human3.6M, CMU Mocap and 3DPW datasets, respectively.


page 1

page 2

page 3

page 4


SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification

Person re-identification via 3D skeletons is an emerging topic with grea...

Centrality Graph Convolutional Networks for Skeleton-based Action Recognition

The topological structure of skeleton data plays a significant role in h...

Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction

3D skeleton-based action recognition and motion prediction are two essen...

IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition

Human interaction recognition is very important in many applications. On...

Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction

We propose novel dynamic multiscale graph neural networks (DMGNN) to pre...

Efficient Hybrid Network: Inducting Scattering Features

Recent work showed that hybrid networks, which combine predefined and le...

Pose Modulated Avatars from Video

It is now possible to reconstruct dynamic human motion and shape from a ...

Please sign up or login with your details

Forgot password? Click here to reset