Saved in:
Bibliographic Details
Main Authors: Yang, Huan, Chen, Jiahui, Ding, Chaofan, Shi, Runhua, Xiong, Siyu, Hong, Qingqi, Mo, Xiaoqi, Di, Xinhan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.17674
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913519686909952
author Yang, Huan
Chen, Jiahui
Ding, Chaofan
Shi, Runhua
Xiong, Siyu
Hong, Qingqi
Mo, Xiaoqi
Di, Xinhan
author_facet Yang, Huan
Chen, Jiahui
Ding, Chaofan
Shi, Runhua
Xiong, Siyu
Hong, Qingqi
Mo, Xiaoqi
Di, Xinhan
contents Gestures are pivotal in enhancing co-speech communication. While recent works have mostly focused on point-level motion transformation or fully supervised motion representations through data-driven approaches, we explore the representation of gestures in co-speech, with a focus on self-supervised representation and pixel-level motion deviation, utilizing a diffusion model which incorporates latent motion features. Our approach leverages self-supervised deviation in latent representation to facilitate hand gestures generation, which are crucial for generating realistic gesture videos. Results of our first experiment demonstrate that our method enhances the quality of generated videos, with an improvement from 2.7 to 4.5% for FGD, DIV, and FVD, and 8.1% for PSNR, 2.5% for SSIM over the current state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17674
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Supervised Learning of Deviation in Latent Representation for Co-speech Gesture Video Generation
Yang, Huan
Chen, Jiahui
Ding, Chaofan
Shi, Runhua
Xiong, Siyu
Hong, Qingqi
Mo, Xiaoqi
Di, Xinhan
Computer Vision and Pattern Recognition
Gestures are pivotal in enhancing co-speech communication. While recent works have mostly focused on point-level motion transformation or fully supervised motion representations through data-driven approaches, we explore the representation of gestures in co-speech, with a focus on self-supervised representation and pixel-level motion deviation, utilizing a diffusion model which incorporates latent motion features. Our approach leverages self-supervised deviation in latent representation to facilitate hand gestures generation, which are crucial for generating realistic gesture videos. Results of our first experiment demonstrate that our method enhances the quality of generated videos, with an improvement from 2.7 to 4.5% for FGD, DIV, and FVD, and 8.1% for PSNR, 2.5% for SSIM over the current state-of-the-art methods.
title Self-Supervised Learning of Deviation in Latent Representation for Co-speech Gesture Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.17674