VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder
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_ | 1866917747204554752 |
|---|---|
| author | Tang, Zhicong Gu, Shuyang Wang, Chunyu Zhang, Ting Bao, Jianmin Chen, Dong Guo, Baining |
| author_facet | Tang, Zhicong Gu, Shuyang Wang, Chunyu Zhang, Ting Bao, Jianmin Chen, Dong Guo, Baining |
| contents | This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view images. The 3D volumes are then trained on a diffusion model for text-to-3D generation using a 3D U-Net. This research further addresses the challenges of inaccurate object captions and high-dimensional feature volumes. The proposed model, trained on the public Objaverse dataset, demonstrates promising outcomes in producing diverse and recognizable samples from text prompts. Notably, it empowers finer control over object part characteristics through textual cues, fostering model creativity by seamlessly combining multiple concepts within a single object. This research significantly contributes to the progress of 3D generation by introducing an efficient, flexible, and scalable representation methodology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_11459 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder Tang, Zhicong Gu, Shuyang Wang, Chunyu Zhang, Ting Bao, Jianmin Chen, Dong Guo, Baining Computer Vision and Pattern Recognition This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view images. The 3D volumes are then trained on a diffusion model for text-to-3D generation using a 3D U-Net. This research further addresses the challenges of inaccurate object captions and high-dimensional feature volumes. The proposed model, trained on the public Objaverse dataset, demonstrates promising outcomes in producing diverse and recognizable samples from text prompts. Notably, it empowers finer control over object part characteristics through textual cues, fostering model creativity by seamlessly combining multiple concepts within a single object. This research significantly contributes to the progress of 3D generation by introducing an efficient, flexible, and scalable representation methodology. |
| title | VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.11459 |