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

• URL: http://arxiv.org/abs/2208.00368v1
• Date: Sun, 31 Jul 2022 05:51:39 GMT
• Title: Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction
• Authors: Maosen Li, Siheng Chen, Zijing Zhang, Lingxi Xie, Qi Tian, Ya Zhang
• Abstract summary: Graph convolutional network based methods that model the body-joints' relations, have recently shown great promise in 3D skeleton-based human motion prediction. We propose a novel skeleton-parted graph scattering network (SPGSN) SPGSN outperforms state-of-the-art methods by remarkable margins of 13.8%, 9.3% and 2.7% in terms of 3D mean per joint position error (MPJPE) on Human3.6M, CMU Mocap and 3DPW datasets, respectively.
• Score: 120.08257447708503
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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%, 9.3% and 2.7% in terms of 3D mean per joint position error (MPJPE) on Human3.6M, CMU Mocap and 3DPW datasets, respectively.

Related papers

• GSpect: Spectral Filtering for Cross-Scale Graph Classification [9.800723513820046]
  We propose GSpect, an advanced spectral graph filtering model for cross-scale graph classification tasks. On open data sets, GSpect improves the performance of classification accuracy by 1.62% on average, and for a maximum of 3.33% on PROTEINS. GSpect fills the gap in cross-scale graph classification studies and has potential to provide assistance in application research like diagnosis of brain disease.
  arXiv  Detail & Related papers  (2024-08-31T03:26:32Z)
• Spatio-temporal MLP-graph network for 3D human pose estimation [8.267311047244881]
  Graph convolutional networks and their variants have shown significant promise in 3D human pose estimation. We introduce a new weighted Jacobi feature rule obtained through graph filtering with implicit propagation fairing. We also employ adjacency modulation with the aim of learning meaningful correlations beyond defined between body joints.
  arXiv  Detail & Related papers  (2023-08-29T14:00:55Z)
• Iterative Graph Filtering Network for 3D Human Pose Estimation [5.177947445379688]
  Graph convolutional networks (GCNs) have proven to be an effective approach for 3D human pose estimation. In this paper, we introduce an iterative graph filtering framework for 3D human pose estimation. Our approach builds upon the idea of iteratively solving graph filtering with Laplacian regularization.
  arXiv  Detail & Related papers  (2023-07-29T20:46:44Z)
• Hierarchical Graph Networks for 3D Human Pose Estimation [50.600944798627786]
  Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton. We argue that this skeletal topology is too sparse to reflect the body structure and suffer from serious 2D-to-3D ambiguity problem. We propose a novel graph convolution network architecture, Hierarchical Graph Networks, to overcome these weaknesses.
  arXiv  Detail & Related papers  (2021-11-23T15:09:03Z)
• Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images [79.70127290464514]
  We decompose the task into two stages, i.e. person localization and pose estimation. And we propose three task-specific graph neural networks for effective message passing. Our approach achieves state-of-the-art performance on CMU Panoptic and Shelf datasets.
  arXiv  Detail & Related papers  (2021-09-13T11:44:07Z)
• Conditional Directed Graph Convolution for 3D Human Pose Estimation [23.376538132362498]
  Graph convolutional networks have significantly improved 3D human pose estimation by representing the human skeleton as an undirected graph. This paper proposes to represent the human skeleton as a directed graph with the joints as nodes and bones as edges that are directed from parent joints to child joints.
  arXiv  Detail & Related papers  (2021-07-16T09:50:40Z)
• 3D Human Pose Regression using Graph Convolutional Network [68.8204255655161]
  We propose a graph convolutional network named PoseGraphNet for 3D human pose regression from 2D poses. Our model's performance is close to the state-of-the-art, but with much fewer parameters.
  arXiv  Detail & Related papers  (2021-05-21T14:41:31Z)
• Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition [79.33539539956186]
  We propose a simple method to disentangle multi-scale graph convolutions and a unified spatial-temporal graph convolutional operator named G3D. By coupling these proposals, we develop a powerful feature extractor named MS-G3D based on which our model outperforms previous state-of-the-art methods on three large-scale datasets.
  arXiv  Detail & Related papers  (2020-03-31T11:28:25Z)
• Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction [102.9787019197379]
  We propose novel dynamic multiscale graph neural networks (DMGNN) to predict 3D skeleton-based human motions. The model is action-category-agnostic and follows an encoder-decoder framework. The proposed DMGNN outperforms state-of-the-art methods in both short and long-term predictions.
  arXiv  Detail & Related papers  (2020-03-17T02:49:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.