RapidMV: Leveraging Spatio-Angular Representations for Efficient and Consistent Text-to-Multi-View Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914063991177216 |
|---|---|
| author | Kim, Seungwook Shi, Yichun Li, Kejie Cho, Minsu Wang, Peng |
| author_facet | Kim, Seungwook Shi, Yichun Li, Kejie Cho, Minsu Wang, Peng |
| contents | Generating synthetic multi-view images from a text prompt is an essential bridge to generating synthetic 3D assets. In this work, we introduce RapidMV, a novel text-to-multi-view generative model that can produce 32 multi-view synthetic images in just around 5 seconds. In essence, we propose a novel spatio-angular latent space, encoding both the spatial appearance and angular viewpoint deviations into a single latent for improved efficiency and multi-view consistency. We achieve effective training of RapidMV by strategically decomposing our training process into multiple steps. We demonstrate that RapidMV outperforms existing methods in terms of consistency and latency, with competitive quality and text-image alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24410 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RapidMV: Leveraging Spatio-Angular Representations for Efficient and Consistent Text-to-Multi-View Synthesis Kim, Seungwook Shi, Yichun Li, Kejie Cho, Minsu Wang, Peng Computer Vision and Pattern Recognition Generating synthetic multi-view images from a text prompt is an essential bridge to generating synthetic 3D assets. In this work, we introduce RapidMV, a novel text-to-multi-view generative model that can produce 32 multi-view synthetic images in just around 5 seconds. In essence, we propose a novel spatio-angular latent space, encoding both the spatial appearance and angular viewpoint deviations into a single latent for improved efficiency and multi-view consistency. We achieve effective training of RapidMV by strategically decomposing our training process into multiple steps. We demonstrate that RapidMV outperforms existing methods in terms of consistency and latency, with competitive quality and text-image alignment. |
| title | RapidMV: Leveraging Spatio-Angular Representations for Efficient and Consistent Text-to-Multi-View Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.24410 |