Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
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_ | 1866929563785756672 |
|---|---|
| author | Wu, Ziyi Rubanova, Yulia Kabra, Rishabh Hudson, Drew A. Gilitschenski, Igor Aytar, Yusuf van Steenkiste, Sjoerd Allen, Kelsey R. Kipf, Thomas |
| author_facet | Wu, Ziyi Rubanova, Yulia Kabra, Rishabh Hudson, Drew A. Gilitschenski, Igor Aytar, Yusuf van Steenkiste, Sjoerd Allen, Kelsey R. Kipf, Thomas |
| contents | We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of individual objects in a scene. Neural Assets are obtained by pooling visual representations of objects from a reference image, such as a frame in a video, and are trained to reconstruct the respective objects in a different image, e.g., a later frame in the video. Importantly, we encode object visuals from the reference image while conditioning on object poses from the target frame. This enables learning disentangled appearance and pose features. Combining visual and 3D pose representations in a sequence-of-tokens format allows us to keep the text-to-image architecture of existing models, with Neural Assets in place of text tokens. By fine-tuning a pre-trained text-to-image diffusion model with this information, our approach enables fine-grained 3D pose and placement control of individual objects in a scene. We further demonstrate that Neural Assets can be transferred and recomposed across different scenes. Our model achieves state-of-the-art multi-object editing results on both synthetic 3D scene datasets, as well as two real-world video datasets (Objectron, Waymo Open). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09292 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models Wu, Ziyi Rubanova, Yulia Kabra, Rishabh Hudson, Drew A. Gilitschenski, Igor Aytar, Yusuf van Steenkiste, Sjoerd Allen, Kelsey R. Kipf, Thomas Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of individual objects in a scene. Neural Assets are obtained by pooling visual representations of objects from a reference image, such as a frame in a video, and are trained to reconstruct the respective objects in a different image, e.g., a later frame in the video. Importantly, we encode object visuals from the reference image while conditioning on object poses from the target frame. This enables learning disentangled appearance and pose features. Combining visual and 3D pose representations in a sequence-of-tokens format allows us to keep the text-to-image architecture of existing models, with Neural Assets in place of text tokens. By fine-tuning a pre-trained text-to-image diffusion model with this information, our approach enables fine-grained 3D pose and placement control of individual objects in a scene. We further demonstrate that Neural Assets can be transferred and recomposed across different scenes. Our model achieves state-of-the-art multi-object editing results on both synthetic 3D scene datasets, as well as two real-world video datasets (Objectron, Waymo Open). |
| title | Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.09292 |