HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Xian, Zhan, Xiaohang, Tang, Jiaxiang, Shan, Ying, Zeng, Gang, Lin, Dahua, Liu, Xihui, Liu, Ziwei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909137156177920
author Liu, Xian
Zhan, Xiaohang
Tang, Jiaxiang
Shan, Ying
Zeng, Gang
Lin, Dahua
Liu, Xihui
Liu, Ziwei
author_facet Liu, Xian
Zhan, Xiaohang
Tang, Jiaxiang
Shan, Ying
Zeng, Gang
Lin, Dahua
Liu, Xihui
Liu, Ziwei
contents Realistic 3D human generation from text prompts is a desirable yet challenging task. Existing methods optimize 3D representations like mesh or neural fields via score distillation sampling (SDS), which suffers from inadequate fine details or excessive training time. In this paper, we propose an efficient yet effective framework, HumanGaussian, that generates high-quality 3D humans with fine-grained geometry and realistic appearance. Our key insight is that 3D Gaussian Splatting is an efficient renderer with periodic Gaussian shrinkage or growing, where such adaptive density control can be naturally guided by intrinsic human structures. Specifically, 1) we first propose a Structure-Aware SDS that simultaneously optimizes human appearance and geometry. The multi-modal score function from both RGB and depth space is leveraged to distill the Gaussian densification and pruning process. 2) Moreover, we devise an Annealed Negative Prompt Guidance by decomposing SDS into a noisier generative score and a cleaner classifier score, which well addresses the over-saturation issue. The floating artifacts are further eliminated based on Gaussian size in a prune-only phase to enhance generation smoothness. Extensive experiments demonstrate the superior efficiency and competitive quality of our framework, rendering vivid 3D humans under diverse scenarios. Project Page: https://alvinliu0.github.io/projects/HumanGaussian
format Preprint
id arxiv_https___arxiv_org_abs_2311_17061
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
Liu, Xian
Zhan, Xiaohang
Tang, Jiaxiang
Shan, Ying
Zeng, Gang
Lin, Dahua
Liu, Xihui
Liu, Ziwei
Computer Vision and Pattern Recognition
Realistic 3D human generation from text prompts is a desirable yet challenging task. Existing methods optimize 3D representations like mesh or neural fields via score distillation sampling (SDS), which suffers from inadequate fine details or excessive training time. In this paper, we propose an efficient yet effective framework, HumanGaussian, that generates high-quality 3D humans with fine-grained geometry and realistic appearance. Our key insight is that 3D Gaussian Splatting is an efficient renderer with periodic Gaussian shrinkage or growing, where such adaptive density control can be naturally guided by intrinsic human structures. Specifically, 1) we first propose a Structure-Aware SDS that simultaneously optimizes human appearance and geometry. The multi-modal score function from both RGB and depth space is leveraged to distill the Gaussian densification and pruning process. 2) Moreover, we devise an Annealed Negative Prompt Guidance by decomposing SDS into a noisier generative score and a cleaner classifier score, which well addresses the over-saturation issue. The floating artifacts are further eliminated based on Gaussian size in a prune-only phase to enhance generation smoothness. Extensive experiments demonstrate the superior efficiency and competitive quality of our framework, rendering vivid 3D humans under diverse scenarios. Project Page: https://alvinliu0.github.io/projects/HumanGaussian
title HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.17061