NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912419729637376 |
|---|---|
| author | Yang, Yuxiao Li, Peihao Zhang, Yuhong Lu, Junzhe He, Xianglong Qin, Minghan Wang, Weitao Wang, Haoqian |
| author_facet | Yang, Yuxiao Li, Peihao Zhang, Yuhong Lu, Junzhe He, Xianglong Qin, Minghan Wang, Weitao Wang, Haoqian |
| contents | 3D AI-generated content (AIGC) has made it increasingly accessible for anyone to become a 3D content creator. While recent methods leverage Score Distillation Sampling to distill 3D objects from pretrained image diffusion models, they often suffer from inadequate 3D priors, leading to insufficient multi-view consistency. In this work, we introduce NOVA3D, an innovative single-image-to-3D generation framework. Our key insight lies in leveraging strong 3D priors from a pretrained video diffusion model and integrating geometric information during multi-view video fine-tuning. To facilitate information exchange between color and geometric domains, we propose the Geometry-Temporal Alignment (GTA) attention mechanism, thereby improving generalization and multi-view consistency. Moreover, we introduce the de-conflict geometry fusion algorithm, which improves texture fidelity by addressing multi-view inaccuracies and resolving discrepancies in pose alignment. Extensive experiments validate the superiority of NOVA3D over existing baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07698 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation Yang, Yuxiao Li, Peihao Zhang, Yuhong Lu, Junzhe He, Xianglong Qin, Minghan Wang, Weitao Wang, Haoqian Computer Vision and Pattern Recognition Artificial Intelligence 3D AI-generated content (AIGC) has made it increasingly accessible for anyone to become a 3D content creator. While recent methods leverage Score Distillation Sampling to distill 3D objects from pretrained image diffusion models, they often suffer from inadequate 3D priors, leading to insufficient multi-view consistency. In this work, we introduce NOVA3D, an innovative single-image-to-3D generation framework. Our key insight lies in leveraging strong 3D priors from a pretrained video diffusion model and integrating geometric information during multi-view video fine-tuning. To facilitate information exchange between color and geometric domains, we propose the Geometry-Temporal Alignment (GTA) attention mechanism, thereby improving generalization and multi-view consistency. Moreover, we introduce the de-conflict geometry fusion algorithm, which improves texture fidelity by addressing multi-view inaccuracies and resolving discrepancies in pose alignment. Extensive experiments validate the superiority of NOVA3D over existing baselines. |
| title | NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.07698 |