ControlDreamer: Blending Geometry and Style in Text-to-3D
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911999761317888 |
|---|---|
| author | Oh, Yeongtak Choi, Jooyoung Kim, Yongsung Park, Minjun Shin, Chaehun Yoon, Sungroh |
| author_facet | Oh, Yeongtak Choi, Jooyoung Kim, Yongsung Park, Minjun Shin, Chaehun Yoon, Sungroh |
| contents | Recent advancements in text-to-3D generation have significantly contributed to the automation and democratization of 3D content creation. Building upon these developments, we aim to address the limitations of current methods in blending geometries and styles in text-to-3D generation. We introduce multi-view ControlNet, a novel depth-aware multi-view diffusion model trained on generated datasets from a carefully curated text corpus. Our multi-view ControlNet is then integrated into our two-stage pipeline, ControlDreamer, enabling text-guided generation of stylized 3D models. Additionally, we present a comprehensive benchmark for 3D style editing, encompassing a broad range of subjects, including objects, animals, and characters, to further facilitate research on diverse 3D generation. Our comparative analysis reveals that this new pipeline outperforms existing text-to-3D methods as evidenced by human evaluations and CLIP score metrics. Project page: https://controldreamer.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_01129 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | ControlDreamer: Blending Geometry and Style in Text-to-3D Oh, Yeongtak Choi, Jooyoung Kim, Yongsung Park, Minjun Shin, Chaehun Yoon, Sungroh Computer Vision and Pattern Recognition Recent advancements in text-to-3D generation have significantly contributed to the automation and democratization of 3D content creation. Building upon these developments, we aim to address the limitations of current methods in blending geometries and styles in text-to-3D generation. We introduce multi-view ControlNet, a novel depth-aware multi-view diffusion model trained on generated datasets from a carefully curated text corpus. Our multi-view ControlNet is then integrated into our two-stage pipeline, ControlDreamer, enabling text-guided generation of stylized 3D models. Additionally, we present a comprehensive benchmark for 3D style editing, encompassing a broad range of subjects, including objects, animals, and characters, to further facilitate research on diverse 3D generation. Our comparative analysis reveals that this new pipeline outperforms existing text-to-3D methods as evidenced by human evaluations and CLIP score metrics. Project page: https://controldreamer.github.io |
| title | ControlDreamer: Blending Geometry and Style in Text-to-3D |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.01129 |