Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Pengzhi, Tang, Chengshuai, Huang, Qinxuan, Li, Zhiheng
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.10508
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909205858877440
author Li, Pengzhi
Tang, Chengshuai
Huang, Qinxuan
Li, Zhiheng
author_facet Li, Pengzhi
Tang, Chengshuai
Huang, Qinxuan
Li, Zhiheng
contents In this paper, we explore the existing challenges in 3D artistic scene generation by introducing ART3D, a novel framework that combines diffusion models and 3D Gaussian splatting techniques. Our method effectively bridges the gap between artistic and realistic images through an innovative image semantic transfer algorithm. By leveraging depth information and an initial artistic image, we generate a point cloud map, addressing domain differences. Additionally, we propose a depth consistency module to enhance 3D scene consistency. Finally, the 3D scene serves as initial points for optimizing Gaussian splats. Experimental results demonstrate ART3D's superior performance in both content and structural consistency metrics when compared to existing methods. ART3D significantly advances the field of AI in art creation by providing an innovative solution for generating high-quality 3D artistic scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10508
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ART3D: 3D Gaussian Splatting for Text-Guided Artistic Scenes Generation
Li, Pengzhi
Tang, Chengshuai
Huang, Qinxuan
Li, Zhiheng
Computer Vision and Pattern Recognition
In this paper, we explore the existing challenges in 3D artistic scene generation by introducing ART3D, a novel framework that combines diffusion models and 3D Gaussian splatting techniques. Our method effectively bridges the gap between artistic and realistic images through an innovative image semantic transfer algorithm. By leveraging depth information and an initial artistic image, we generate a point cloud map, addressing domain differences. Additionally, we propose a depth consistency module to enhance 3D scene consistency. Finally, the 3D scene serves as initial points for optimizing Gaussian splats. Experimental results demonstrate ART3D's superior performance in both content and structural consistency metrics when compared to existing methods. ART3D significantly advances the field of AI in art creation by providing an innovative solution for generating high-quality 3D artistic scenes.
title ART3D: 3D Gaussian Splatting for Text-Guided Artistic Scenes Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.10508