GEN3D: Generating Domain-Free 3D Scenes from a Single Image
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918208135495680 |
|---|---|
| author | Zhang, Yuxin Lu, Ziyu Duan, Hongbo Fan, Keyu Luo, Pengting Zhuang, Peiyu Yang, Mengyu Liu, Houde |
| author_facet | Zhang, Yuxin Lu, Ziyu Duan, Hongbo Fan, Keyu Luo, Pengting Zhuang, Peiyu Yang, Mengyu Liu, Houde |
| contents | Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. Additionally, 3D scene generation is vital for advancing embodied AI and world models, which depend on diverse, high-quality scenes for learning and evaluation. In this work, we propose Gen3d, a novel method for generation of high-quality, wide-scope, and generic 3D scenes from a single image. After the initial point cloud is created by lifting the RGBD image, Gen3d maintains and expands its world model. The 3D scene is finalized through optimizing a Gaussian splatting representation. Extensive experiments on diverse datasets demonstrate the strong generalization capability and superior performance of our method in generating a world model and Synthesizing high-fidelity and consistent novel views. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14291 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GEN3D: Generating Domain-Free 3D Scenes from a Single Image Zhang, Yuxin Lu, Ziyu Duan, Hongbo Fan, Keyu Luo, Pengting Zhuang, Peiyu Yang, Mengyu Liu, Houde Computer Vision and Pattern Recognition Artificial Intelligence Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. Additionally, 3D scene generation is vital for advancing embodied AI and world models, which depend on diverse, high-quality scenes for learning and evaluation. In this work, we propose Gen3d, a novel method for generation of high-quality, wide-scope, and generic 3D scenes from a single image. After the initial point cloud is created by lifting the RGBD image, Gen3d maintains and expands its world model. The 3D scene is finalized through optimizing a Gaussian splatting representation. Extensive experiments on diverse datasets demonstrate the strong generalization capability and superior performance of our method in generating a world model and Synthesizing high-fidelity and consistent novel views. |
| title | GEN3D: Generating Domain-Free 3D Scenes from a Single Image |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.14291 |