DreamGaussian4D: Generative 4D Gaussian Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929379685171200 |
|---|---|
| author | Ren, Jiawei Pan, Liang Tang, Jiaxiang Zhang, Chi Cao, Ang Zeng, Gang Liu, Ziwei |
| author_facet | Ren, Jiawei Pan, Liang Tang, Jiaxiang Zhang, Chi Cao, Ang Zeng, Gang Liu, Ziwei |
| contents | 4D content generation has achieved remarkable progress recently. However, existing methods suffer from long optimization times, a lack of motion controllability, and a low quality of details. In this paper, we introduce DreamGaussian4D (DG4D), an efficient 4D generation framework that builds on Gaussian Splatting (GS). Our key insight is that combining explicit modeling of spatial transformations with static GS makes an efficient and powerful representation for 4D generation. Moreover, video generation methods have the potential to offer valuable spatial-temporal priors, enhancing the high-quality 4D generation. Specifically, we propose an integral framework with two major modules: 1) Image-to-4D GS - we initially generate static GS with DreamGaussianHD, followed by HexPlane-based dynamic generation with Gaussian deformation; and 2) Video-to-Video Texture Refinement - we refine the generated UV-space texture maps and meanwhile enhance their temporal consistency by utilizing a pre-trained image-to-video diffusion model. Notably, DG4D reduces the optimization time from several hours to just a few minutes, allows the generated 3D motion to be visually controlled, and produces animated meshes that can be realistically rendered in 3D engines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_17142 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DreamGaussian4D: Generative 4D Gaussian Splatting Ren, Jiawei Pan, Liang Tang, Jiaxiang Zhang, Chi Cao, Ang Zeng, Gang Liu, Ziwei Computer Vision and Pattern Recognition Graphics 4D content generation has achieved remarkable progress recently. However, existing methods suffer from long optimization times, a lack of motion controllability, and a low quality of details. In this paper, we introduce DreamGaussian4D (DG4D), an efficient 4D generation framework that builds on Gaussian Splatting (GS). Our key insight is that combining explicit modeling of spatial transformations with static GS makes an efficient and powerful representation for 4D generation. Moreover, video generation methods have the potential to offer valuable spatial-temporal priors, enhancing the high-quality 4D generation. Specifically, we propose an integral framework with two major modules: 1) Image-to-4D GS - we initially generate static GS with DreamGaussianHD, followed by HexPlane-based dynamic generation with Gaussian deformation; and 2) Video-to-Video Texture Refinement - we refine the generated UV-space texture maps and meanwhile enhance their temporal consistency by utilizing a pre-trained image-to-video diffusion model. Notably, DG4D reduces the optimization time from several hours to just a few minutes, allows the generated 3D motion to be visually controlled, and produces animated meshes that can be realistically rendered in 3D engines. |
| title | DreamGaussian4D: Generative 4D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2312.17142 |