DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909134273642496 |
|---|---|
| author | Tang, Jiapeng Nie, Yinyu Markhasin, Lev Dai, Angela Thies, Justus Nießner, Matthias |
| author_facet | Tang, Jiapeng Nie, Yinyu Markhasin, Lev Dai, Angela Thies, Justus Nießner, Matthias |
| contents | We present DiffuScene for indoor 3D scene synthesis based on a novel scene configuration denoising diffusion model. It generates 3D instance properties stored in an unordered object set and retrieves the most similar geometry for each object configuration, which is characterized as a concatenation of different attributes, including location, size, orientation, semantics, and geometry features. We introduce a diffusion network to synthesize a collection of 3D indoor objects by denoising a set of unordered object attributes. Unordered parametrization simplifies and eases the joint distribution approximation. The shape feature diffusion facilitates natural object placements, including symmetries. Our method enables many downstream applications, including scene completion, scene arrangement, and text-conditioned scene synthesis. Experiments on the 3D-FRONT dataset show that our method can synthesize more physically plausible and diverse indoor scenes than state-of-the-art methods. Extensive ablation studies verify the effectiveness of our design choice in scene diffusion models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_14207 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis Tang, Jiapeng Nie, Yinyu Markhasin, Lev Dai, Angela Thies, Justus Nießner, Matthias Computer Vision and Pattern Recognition We present DiffuScene for indoor 3D scene synthesis based on a novel scene configuration denoising diffusion model. It generates 3D instance properties stored in an unordered object set and retrieves the most similar geometry for each object configuration, which is characterized as a concatenation of different attributes, including location, size, orientation, semantics, and geometry features. We introduce a diffusion network to synthesize a collection of 3D indoor objects by denoising a set of unordered object attributes. Unordered parametrization simplifies and eases the joint distribution approximation. The shape feature diffusion facilitates natural object placements, including symmetries. Our method enables many downstream applications, including scene completion, scene arrangement, and text-conditioned scene synthesis. Experiments on the 3D-FRONT dataset show that our method can synthesize more physically plausible and diverse indoor scenes than state-of-the-art methods. Extensive ablation studies verify the effectiveness of our design choice in scene diffusion models. |
| title | DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.14207 |