GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Xiaoyu, Ran, Xingjian, Xiong, Yajiao, He, Jinlin, Lin, Zhiwei, Wang, Yongtao, Sun, Deqing, Yang, Ming-Hsuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917690357055488
author Zhou, Xiaoyu
Ran, Xingjian
Xiong, Yajiao
He, Jinlin
Lin, Zhiwei
Wang, Yongtao
Sun, Deqing
Yang, Ming-Hsuan
author_facet Zhou, Xiaoyu
Ran, Xingjian
Xiong, Yajiao
He, Jinlin
Lin, Zhiwei
Wang, Yongtao
Sun, Deqing
Yang, Ming-Hsuan
contents We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. We first utilize large language models (LLMs) to generate the initial layout and introduce a layout-guided 3D Gaussian representation for 3D content generation with adaptive geometric constraints. We then propose an instance-scene compositional optimization mechanism with conditioned diffusion to collaboratively generate realistic 3D scenes with consistent geometry, texture, scale, and accurate interactions among multiple objects while simultaneously adjusting the coarse layout priors extracted from the LLMs to align with the generated scene. Experiments show that GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing while ensuring the high fidelity of object-level entities within the scene. The source codes and models will be available at gala3d.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2402_07207
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting
Zhou, Xiaoyu
Ran, Xingjian
Xiong, Yajiao
He, Jinlin
Lin, Zhiwei
Wang, Yongtao
Sun, Deqing
Yang, Ming-Hsuan
Computer Vision and Pattern Recognition
We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. We first utilize large language models (LLMs) to generate the initial layout and introduce a layout-guided 3D Gaussian representation for 3D content generation with adaptive geometric constraints. We then propose an instance-scene compositional optimization mechanism with conditioned diffusion to collaboratively generate realistic 3D scenes with consistent geometry, texture, scale, and accurate interactions among multiple objects while simultaneously adjusting the coarse layout priors extracted from the LLMs to align with the generated scene. Experiments show that GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing while ensuring the high fidelity of object-level entities within the scene. The source codes and models will be available at gala3d.github.io.
title GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.07207