SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913315339370496 |
|---|---|
| author | Liu, Yuan Lin, Cheng Zeng, Zijiao Long, Xiaoxiao Liu, Lingjie Komura, Taku Wang, Wenping |
| author_facet | Liu, Yuan Lin, Cheng Zeng, Zijiao Long, Xiaoxiao Liu, Lingjie Komura, Taku Wang, Wenping |
| contents | In this paper, we present a novel diffusion model called that generates multiview-consistent images from a single-view image. Using pretrained large-scale 2D diffusion models, recent work Zero123 demonstrates the ability to generate plausible novel views from a single-view image of an object. However, maintaining consistency in geometry and colors for the generated images remains a challenge. To address this issue, we propose a synchronized multiview diffusion model that models the joint probability distribution of multiview images, enabling the generation of multiview-consistent images in a single reverse process. SyncDreamer synchronizes the intermediate states of all the generated images at every step of the reverse process through a 3D-aware feature attention mechanism that correlates the corresponding features across different views. Experiments show that SyncDreamer generates images with high consistency across different views, thus making it well-suited for various 3D generation tasks such as novel-view-synthesis, text-to-3D, and image-to-3D. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_03453 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SyncDreamer: Generating Multiview-consistent Images from a Single-view Image Liu, Yuan Lin, Cheng Zeng, Zijiao Long, Xiaoxiao Liu, Lingjie Komura, Taku Wang, Wenping Computer Vision and Pattern Recognition Artificial Intelligence Graphics In this paper, we present a novel diffusion model called that generates multiview-consistent images from a single-view image. Using pretrained large-scale 2D diffusion models, recent work Zero123 demonstrates the ability to generate plausible novel views from a single-view image of an object. However, maintaining consistency in geometry and colors for the generated images remains a challenge. To address this issue, we propose a synchronized multiview diffusion model that models the joint probability distribution of multiview images, enabling the generation of multiview-consistent images in a single reverse process. SyncDreamer synchronizes the intermediate states of all the generated images at every step of the reverse process through a 3D-aware feature attention mechanism that correlates the corresponding features across different views. Experiments show that SyncDreamer generates images with high consistency across different views, thus making it well-suited for various 3D generation tasks such as novel-view-synthesis, text-to-3D, and image-to-3D. |
| title | SyncDreamer: Generating Multiview-consistent Images from a Single-view Image |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2309.03453 |