DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909267117735936 |
|---|---|
| author | Zhou, Shijie Fan, Zhiwen Xu, Dejia Chang, Haoran Chari, Pradyumna Bharadwaj, Tejas You, Suya Wang, Zhangyang Kadambi, Achuta |
| author_facet | Zhou, Shijie Fan, Zhiwen Xu, Dejia Chang, Haoran Chari, Pradyumna Bharadwaj, Tejas You, Suya Wang, Zhangyang Kadambi, Achuta |
| contents | The increasing demand for virtual reality applications has highlighted the significance of crafting immersive 3D assets. We present a text-to-3D 360$^{\circ}$ scene generation pipeline that facilitates the creation of comprehensive 360$^{\circ}$ scenes for in-the-wild environments in a matter of minutes. Our approach utilizes the generative power of a 2D diffusion model and prompt self-refinement to create a high-quality and globally coherent panoramic image. This image acts as a preliminary "flat" (2D) scene representation. Subsequently, it is lifted into 3D Gaussians, employing splatting techniques to enable real-time exploration. To produce consistent 3D geometry, our pipeline constructs a spatially coherent structure by aligning the 2D monocular depth into a globally optimized point cloud. This point cloud serves as the initial state for the centroids of 3D Gaussians. In order to address invisible issues inherent in single-view inputs, we impose semantic and geometric constraints on both synthesized and input camera views as regularizations. These guide the optimization of Gaussians, aiding in the reconstruction of unseen regions. In summary, our method offers a globally consistent 3D scene within a 360$^{\circ}$ perspective, providing an enhanced immersive experience over existing techniques. Project website at: http://dreamscene360.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06903 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting Zhou, Shijie Fan, Zhiwen Xu, Dejia Chang, Haoran Chari, Pradyumna Bharadwaj, Tejas You, Suya Wang, Zhangyang Kadambi, Achuta Computer Vision and Pattern Recognition Artificial Intelligence The increasing demand for virtual reality applications has highlighted the significance of crafting immersive 3D assets. We present a text-to-3D 360$^{\circ}$ scene generation pipeline that facilitates the creation of comprehensive 360$^{\circ}$ scenes for in-the-wild environments in a matter of minutes. Our approach utilizes the generative power of a 2D diffusion model and prompt self-refinement to create a high-quality and globally coherent panoramic image. This image acts as a preliminary "flat" (2D) scene representation. Subsequently, it is lifted into 3D Gaussians, employing splatting techniques to enable real-time exploration. To produce consistent 3D geometry, our pipeline constructs a spatially coherent structure by aligning the 2D monocular depth into a globally optimized point cloud. This point cloud serves as the initial state for the centroids of 3D Gaussians. In order to address invisible issues inherent in single-view inputs, we impose semantic and geometric constraints on both synthesized and input camera views as regularizations. These guide the optimization of Gaussians, aiding in the reconstruction of unseen regions. In summary, our method offers a globally consistent 3D scene within a 360$^{\circ}$ perspective, providing an enhanced immersive experience over existing techniques. Project website at: http://dreamscene360.github.io/ |
| title | DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2404.06903 |