DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Jiaxiang, Ren, Jiawei, Zhou, Hang, Liu, Ziwei, Zeng, Gang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910389445328896
author Tang, Jiaxiang
Ren, Jiawei
Zhou, Hang
Liu, Ziwei
Zeng, Gang
author_facet Tang, Jiaxiang
Ren, Jiawei
Zhou, Hang
Liu, Ziwei
Zeng, Gang
contents Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Radiance Fields, we demonstrate that the progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks. To further enhance the texture quality and facilitate downstream applications, we introduce an efficient algorithm to convert 3D Gaussians into textured meshes and apply a fine-tuning stage to refine the details. Extensive experiments demonstrate the superior efficiency and competitive generation quality of our proposed approach. Notably, DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2309_16653
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
Tang, Jiaxiang
Ren, Jiawei
Zhou, Hang
Liu, Ziwei
Zeng, Gang
Computer Vision and Pattern Recognition
Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Radiance Fields, we demonstrate that the progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks. To further enhance the texture quality and facilitate downstream applications, we introduce an efficient algorithm to convert 3D Gaussians into textured meshes and apply a fine-tuning stage to refine the details. Extensive experiments demonstrate the superior efficiency and competitive generation quality of our proposed approach. Notably, DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.
title DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.16653