Controllable 3D Placement of Objects with Scene-Aware Diffusion Models
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_ | 1866909660746874880 |
|---|---|
| author | Omran, Mohamed Kalatzis, Dimitris Petersen, Jens Habibian, Amirhossein Wiggers, Auke |
| author_facet | Omran, Mohamed Kalatzis, Dimitris Petersen, Jens Habibian, Amirhossein Wiggers, Auke |
| contents | Image editing approaches have become more powerful and flexible with the advent of powerful text-conditioned generative models. However, placing objects in an environment with a precise location and orientation still remains a challenge, as this typically requires carefully crafted inpainting masks or prompts. In this work, we show that a carefully designed visual map, combined with coarse object masks, is sufficient for high quality object placement. We design a conditioning signal that resolves ambiguities, while being flexible enough to allow for changing of shapes or object orientations. By building on an inpainting model, we leave the background intact by design, in contrast to methods that model objects and background jointly. We demonstrate the effectiveness of our method in the automotive setting, where we compare different conditioning signals in novel object placement tasks. These tasks are designed to measure edit quality not only in terms of appearance, but also in terms of pose and location accuracy, including cases that require non-trivial shape changes. Lastly, we show that fine location control can be combined with appearance control to place existing objects in precise locations in a scene. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21446 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Controllable 3D Placement of Objects with Scene-Aware Diffusion Models Omran, Mohamed Kalatzis, Dimitris Petersen, Jens Habibian, Amirhossein Wiggers, Auke Computer Vision and Pattern Recognition Image editing approaches have become more powerful and flexible with the advent of powerful text-conditioned generative models. However, placing objects in an environment with a precise location and orientation still remains a challenge, as this typically requires carefully crafted inpainting masks or prompts. In this work, we show that a carefully designed visual map, combined with coarse object masks, is sufficient for high quality object placement. We design a conditioning signal that resolves ambiguities, while being flexible enough to allow for changing of shapes or object orientations. By building on an inpainting model, we leave the background intact by design, in contrast to methods that model objects and background jointly. We demonstrate the effectiveness of our method in the automotive setting, where we compare different conditioning signals in novel object placement tasks. These tasks are designed to measure edit quality not only in terms of appearance, but also in terms of pose and location accuracy, including cases that require non-trivial shape changes. Lastly, we show that fine location control can be combined with appearance control to place existing objects in precise locations in a scene. |
| title | Controllable 3D Placement of Objects with Scene-Aware Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.21446 |