ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913350751879168 |
|---|---|
| author | Wang, Zhenwei Wang, Tengfei Hancke, Gerhard Liu, Ziwei Lau, Rynson W. H. |
| author_facet | Wang, Zhenwei Wang, Tengfei Hancke, Gerhard Liu, Ziwei Lau, Rynson W. H. |
| contents | Real-world applications often require a large gallery of 3D assets that share a consistent theme. While remarkable advances have been made in general 3D content creation from text or image, synthesizing customized 3D assets following the shared theme of input 3D exemplars remains an open and challenging problem. In this work, we present ThemeStation, a novel approach for theme-aware 3D-to-3D generation. ThemeStation synthesizes customized 3D assets based on given few exemplars with two goals: 1) unity for generating 3D assets that thematically align with the given exemplars and 2) diversity for generating 3D assets with a high degree of variations. To this end, we design a two-stage framework that draws a concept image first, followed by a reference-informed 3D modeling stage. We propose a novel dual score distillation (DSD) loss to jointly leverage priors from both the input exemplars and the synthesized concept image. Extensive experiments and user studies confirm that ThemeStation surpasses prior works in producing diverse theme-aware 3D models with impressive quality. ThemeStation also enables various applications such as controllable 3D-to-3D generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_15383 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars Wang, Zhenwei Wang, Tengfei Hancke, Gerhard Liu, Ziwei Lau, Rynson W. H. Computer Vision and Pattern Recognition Real-world applications often require a large gallery of 3D assets that share a consistent theme. While remarkable advances have been made in general 3D content creation from text or image, synthesizing customized 3D assets following the shared theme of input 3D exemplars remains an open and challenging problem. In this work, we present ThemeStation, a novel approach for theme-aware 3D-to-3D generation. ThemeStation synthesizes customized 3D assets based on given few exemplars with two goals: 1) unity for generating 3D assets that thematically align with the given exemplars and 2) diversity for generating 3D assets with a high degree of variations. To this end, we design a two-stage framework that draws a concept image first, followed by a reference-informed 3D modeling stage. We propose a novel dual score distillation (DSD) loss to jointly leverage priors from both the input exemplars and the synthesized concept image. Extensive experiments and user studies confirm that ThemeStation surpasses prior works in producing diverse theme-aware 3D models with impressive quality. ThemeStation also enables various applications such as controllable 3D-to-3D generation. |
| title | ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.15383 |