Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.13741 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912966030393344 |
|---|---|
| author | Lee, Jae Yong Scharstein, Daniel Bapat, Akash Hu, Hao Fu, Andrew Zhao, Haoru Sammut, Paul Li, Xiang Jeapes, Stephen Gupta, Anik David, Lior Madhuvarasu, Saketh Joshi, Jay Girish Wither, Jason |
| author_facet | Lee, Jae Yong Scharstein, Daniel Bapat, Akash Hu, Hao Fu, Andrew Zhao, Haoru Sammut, Paul Li, Xiang Jeapes, Stephen Gupta, Anik David, Lior Madhuvarasu, Saketh Joshi, Jay Girish Wither, Jason |
| contents | We present Ego-1K, a large-scale collection of time-synchronized egocentric multiview videos designed to advance neural 3D video synthesis and dynamic scene understanding. The dataset contains nearly 1,000 short egocentric videos captured with a custom rig with 12 synchronized cameras surrounding a 4-camera VR headset worn by the user. Scene content focuses on hand motions and hand-object interactions in different settings. We describe rig design, data processing, and calibration. Our dataset enables new ways to benchmark egocentric scene reconstruction methods, an important research area as smart glasses with multiple cameras become omnipresent. Our experiments demonstrate that our dataset presents unique challenges for existing 3D and 4D novel view synthesis methods due to large disparities and image motion caused by close dynamic objects and rig egomotion. Our dataset supports future research in this challenging domain. It is available at https://huggingface.co/datasets/facebook/ego-1k. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13741 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Ego-1K -- A Large-Scale Multiview Video Dataset for Egocentric Vision Lee, Jae Yong Scharstein, Daniel Bapat, Akash Hu, Hao Fu, Andrew Zhao, Haoru Sammut, Paul Li, Xiang Jeapes, Stephen Gupta, Anik David, Lior Madhuvarasu, Saketh Joshi, Jay Girish Wither, Jason Computer Vision and Pattern Recognition We present Ego-1K, a large-scale collection of time-synchronized egocentric multiview videos designed to advance neural 3D video synthesis and dynamic scene understanding. The dataset contains nearly 1,000 short egocentric videos captured with a custom rig with 12 synchronized cameras surrounding a 4-camera VR headset worn by the user. Scene content focuses on hand motions and hand-object interactions in different settings. We describe rig design, data processing, and calibration. Our dataset enables new ways to benchmark egocentric scene reconstruction methods, an important research area as smart glasses with multiple cameras become omnipresent. Our experiments demonstrate that our dataset presents unique challenges for existing 3D and 4D novel view synthesis methods due to large disparities and image motion caused by close dynamic objects and rig egomotion. Our dataset supports future research in this challenging domain. It is available at https://huggingface.co/datasets/facebook/ego-1k. |
| title | Ego-1K -- A Large-Scale Multiview Video Dataset for Egocentric Vision |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.13741 |