MegaScenes: Scene-Level View Synthesis at Scale
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917755017494528 |
|---|---|
| author | Tung, Joseph Chou, Gene Cai, Ruojin Yang, Guandao Zhang, Kai Wetzstein, Gordon Hariharan, Bharath Snavely, Noah |
| author_facet | Tung, Joseph Chou, Gene Cai, Ruojin Yang, Guandao Zhang, Kai Wetzstein, Gordon Hariharan, Bharath Snavely, Noah |
| contents | Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. Recently, pose-conditioned diffusion models have led to significant progress by extracting 3D information from 2D foundation models, but these methods are limited by the lack of scene-level training data. Common dataset choices either consist of isolated objects (Objaverse), or of object-centric scenes with limited pose distributions (DTU, CO3D). In this paper, we create a large-scale scene-level dataset from Internet photo collections, called MegaScenes, which contains over 100K structure from motion (SfM) reconstructions from around the world. Internet photos represent a scalable data source but come with challenges such as lighting and transient objects. We address these issues to further create a subset suitable for the task of NVS. Additionally, we analyze failure cases of state-of-the-art NVS methods and significantly improve generation consistency. Through extensive experiments, we validate the effectiveness of both our dataset and method on generating in-the-wild scenes. For details on the dataset and code, see our project page at https://megascenes.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11819 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MegaScenes: Scene-Level View Synthesis at Scale Tung, Joseph Chou, Gene Cai, Ruojin Yang, Guandao Zhang, Kai Wetzstein, Gordon Hariharan, Bharath Snavely, Noah Computer Vision and Pattern Recognition Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. Recently, pose-conditioned diffusion models have led to significant progress by extracting 3D information from 2D foundation models, but these methods are limited by the lack of scene-level training data. Common dataset choices either consist of isolated objects (Objaverse), or of object-centric scenes with limited pose distributions (DTU, CO3D). In this paper, we create a large-scale scene-level dataset from Internet photo collections, called MegaScenes, which contains over 100K structure from motion (SfM) reconstructions from around the world. Internet photos represent a scalable data source but come with challenges such as lighting and transient objects. We address these issues to further create a subset suitable for the task of NVS. Additionally, we analyze failure cases of state-of-the-art NVS methods and significantly improve generation consistency. Through extensive experiments, we validate the effectiveness of both our dataset and method on generating in-the-wild scenes. For details on the dataset and code, see our project page at https://megascenes.github.io. |
| title | MegaScenes: Scene-Level View Synthesis at Scale |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.11819 |