Towards motion from video diffusion models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Janson, Paul, Popa, Tiberiu, Belilovsky, Eugene
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909396400865280
author Janson, Paul
Popa, Tiberiu
Belilovsky, Eugene
author_facet Janson, Paul
Popa, Tiberiu
Belilovsky, Eugene
contents Text-conditioned video diffusion models have emerged as a powerful tool in the realm of video generation and editing. But their ability to capture the nuances of human movement remains under-explored. Indeed the ability of these models to faithfully model an array of text prompts can lead to a wide host of applications in human and character animation. In this work, we take initial steps to investigate whether these models can effectively guide the synthesis of realistic human body animations. Specifically we propose to synthesize human motion by deforming an SMPL-X body representation guided by Score distillation sampling (SDS) calculated using a video diffusion model. By analyzing the fidelity of the resulting animations, we gain insights into the extent to which we can obtain motion using publicly available text-to-video diffusion models using SDS. Our findings shed light on the potential and limitations of these models for generating diverse and plausible human motions, paving the way for further research in this exciting area.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12831
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards motion from video diffusion models
Janson, Paul
Popa, Tiberiu
Belilovsky, Eugene
Computer Vision and Pattern Recognition
Text-conditioned video diffusion models have emerged as a powerful tool in the realm of video generation and editing. But their ability to capture the nuances of human movement remains under-explored. Indeed the ability of these models to faithfully model an array of text prompts can lead to a wide host of applications in human and character animation. In this work, we take initial steps to investigate whether these models can effectively guide the synthesis of realistic human body animations. Specifically we propose to synthesize human motion by deforming an SMPL-X body representation guided by Score distillation sampling (SDS) calculated using a video diffusion model. By analyzing the fidelity of the resulting animations, we gain insights into the extent to which we can obtain motion using publicly available text-to-video diffusion models using SDS. Our findings shed light on the potential and limitations of these models for generating diverse and plausible human motions, paving the way for further research in this exciting area.
title Towards motion from video diffusion models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.12831