Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifold

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Jiayi, Weng, Dongdong, Du, Qiuxin, Tian, Zeyu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916524899434496
author Zhao, Jiayi
Weng, Dongdong
Du, Qiuxin
Tian, Zeyu
author_facet Zhao, Jiayi
Weng, Dongdong
Du, Qiuxin
Tian, Zeyu
contents Human motion generation involves creating natural sequences of human body poses, widely used in gaming, virtual reality, and human-computer interaction. It aims to produce lifelike virtual characters with realistic movements, enhancing virtual agents and immersive experiences. While previous work has focused on motion generation based on signals like movement, music, text, or scene background, the complexity of human motion and its relationships with these signals often results in unsatisfactory outputs. Manifold learning offers a solution by reducing data dimensionality and capturing subspaces of effective motion. In this review, we present a comprehensive overview of manifold applications in human motion generation, one of the first in this domain. We explore methods for extracting manifolds from unstructured data, their application in motion generation, and discuss their advantages and future directions. This survey aims to provide a broad perspective on the field and stimulate new approaches to ongoing challenges.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10458
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifold
Zhao, Jiayi
Weng, Dongdong
Du, Qiuxin
Tian, Zeyu
Computer Vision and Pattern Recognition
Graphics
Human-Computer Interaction
Human motion generation involves creating natural sequences of human body poses, widely used in gaming, virtual reality, and human-computer interaction. It aims to produce lifelike virtual characters with realistic movements, enhancing virtual agents and immersive experiences. While previous work has focused on motion generation based on signals like movement, music, text, or scene background, the complexity of human motion and its relationships with these signals often results in unsatisfactory outputs. Manifold learning offers a solution by reducing data dimensionality and capturing subspaces of effective motion. In this review, we present a comprehensive overview of manifold applications in human motion generation, one of the first in this domain. We explore methods for extracting manifolds from unstructured data, their application in motion generation, and discuss their advantages and future directions. This survey aims to provide a broad perspective on the field and stimulate new approaches to ongoing challenges.
title Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifold
topic Computer Vision and Pattern Recognition
Graphics
Human-Computer Interaction
url https://arxiv.org/abs/2412.10458