DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision
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_ | 1866929195502796800 |
|---|---|
| author | Ling, Lu Sheng, Yichen Tu, Zhi Zhao, Wentian Xin, Cheng Wan, Kun Yu, Lantao Guo, Qianyu Yu, Zixun Lu, Yawen Li, Xuanmao Sun, Xingpeng Ashok, Rohan Mukherjee, Aniruddha Kang, Hao Kong, Xiangrui Hua, Gang Zhang, Tianyi Benes, Bedrich Bera, Aniket |
| author_facet | Ling, Lu Sheng, Yichen Tu, Zhi Zhao, Wentian Xin, Cheng Wan, Kun Yu, Lantao Guo, Qianyu Yu, Zixun Lu, Yawen Li, Xuanmao Sun, Xingpeng Ashok, Rohan Mukherjee, Aniruddha Kang, Hao Kong, Xiangrui Hua, Gang Zhang, Tianyi Benes, Bedrich Bera, Aniket |
| contents | We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation. Our DL3DV-10K dataset, benchmark results, and models will be publicly accessible at https://dl3dv-10k.github.io/DL3DV-10K/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_16256 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision Ling, Lu Sheng, Yichen Tu, Zhi Zhao, Wentian Xin, Cheng Wan, Kun Yu, Lantao Guo, Qianyu Yu, Zixun Lu, Yawen Li, Xuanmao Sun, Xingpeng Ashok, Rohan Mukherjee, Aniruddha Kang, Hao Kong, Xiangrui Hua, Gang Zhang, Tianyi Benes, Bedrich Bera, Aniket Computer Vision and Pattern Recognition Artificial Intelligence We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation. Our DL3DV-10K dataset, benchmark results, and models will be publicly accessible at https://dl3dv-10k.github.io/DL3DV-10K/. |
| title | DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2312.16256 |