Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
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_ | 1866910367508070400 |
|---|---|
| author | Ye, Jianglong Wang, Peng Li, Kejie Shi, Yichun Wang, Heng |
| author_facet | Ye, Jianglong Wang, Peng Li, Kejie Shi, Yichun Wang, Heng |
| contents | Zero-shot novel view synthesis (NVS) from a single image is an essential problem in 3D object understanding. While recent approaches that leverage pre-trained generative models can synthesize high-quality novel views from in-the-wild inputs, they still struggle to maintain 3D consistency across different views. In this paper, we present Consistent-1-to-3, which is a generative framework that significantly mitigates this issue. Specifically, we decompose the NVS task into two stages: (i) transforming observed regions to a novel view, and (ii) hallucinating unseen regions. We design a scene representation transformer and view-conditioned diffusion model for performing these two stages respectively. Inside the models, to enforce 3D consistency, we propose to employ epipolor-guided attention to incorporate geometry constraints, and multi-view attention to better aggregate multi-view information. Finally, we design a hierarchy generation paradigm to generate long sequences of consistent views, allowing a full 360-degree observation of the provided object image. Qualitative and quantitative evaluation over multiple datasets demonstrates the effectiveness of the proposed mechanisms against state-of-the-art approaches. Our project page is at https://jianglongye.com/consistent123/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_03020 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models Ye, Jianglong Wang, Peng Li, Kejie Shi, Yichun Wang, Heng Computer Vision and Pattern Recognition Zero-shot novel view synthesis (NVS) from a single image is an essential problem in 3D object understanding. While recent approaches that leverage pre-trained generative models can synthesize high-quality novel views from in-the-wild inputs, they still struggle to maintain 3D consistency across different views. In this paper, we present Consistent-1-to-3, which is a generative framework that significantly mitigates this issue. Specifically, we decompose the NVS task into two stages: (i) transforming observed regions to a novel view, and (ii) hallucinating unseen regions. We design a scene representation transformer and view-conditioned diffusion model for performing these two stages respectively. Inside the models, to enforce 3D consistency, we propose to employ epipolor-guided attention to incorporate geometry constraints, and multi-view attention to better aggregate multi-view information. Finally, we design a hierarchy generation paradigm to generate long sequences of consistent views, allowing a full 360-degree observation of the provided object image. Qualitative and quantitative evaluation over multiple datasets demonstrates the effectiveness of the proposed mechanisms against state-of-the-art approaches. Our project page is at https://jianglongye.com/consistent123/ |
| title | Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.03020 |