Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.11301 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917141514551296 |
|---|---|
| author | Li, Bate Zhong, Houqiang Cheng, Zhengxue Hu, Qiang Wang, Qiang Song, Li Zhang, Wenjun |
| author_facet | Li, Bate Zhong, Houqiang Cheng, Zhengxue Hu, Qiang Wang, Qiang Song, Li Zhang, Wenjun |
| contents | Multi-view egocentric dynamic scene reconstruction holds significant research value for applications in holographic documentation of social interactions. However, existing reconstruction datasets focus on static multi-view or single-egocentric view setups, lacking multi-view egocentric datasets for dynamic scene reconstruction. Therefore, we present MultiEgo, the first multi-view egocentric dataset for 4D dynamic scene reconstruction. The dataset comprises five canonical social interaction scenes: meetings, performances, and a presentation. Each scene provides five authentic egocentric videos captured by participants wearing AR glasses. We design a hardware-based data acquisition system and processing pipeline, achieving sub-millisecond temporal synchronization across views, coupled with accurate pose annotations. Experiment validation demonstrates the practical utility and effectiveness of our dataset for free-viewpoint video (FVV) applications, establishing MultiEgo as a foundational resource for advancing multi-view egocentric dynamic scene reconstruction research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11301 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MultiEgo: A Multi-View Egocentric Video Dataset for 4D Scene Reconstruction Li, Bate Zhong, Houqiang Cheng, Zhengxue Hu, Qiang Wang, Qiang Song, Li Zhang, Wenjun Computer Vision and Pattern Recognition Multi-view egocentric dynamic scene reconstruction holds significant research value for applications in holographic documentation of social interactions. However, existing reconstruction datasets focus on static multi-view or single-egocentric view setups, lacking multi-view egocentric datasets for dynamic scene reconstruction. Therefore, we present MultiEgo, the first multi-view egocentric dataset for 4D dynamic scene reconstruction. The dataset comprises five canonical social interaction scenes: meetings, performances, and a presentation. Each scene provides five authentic egocentric videos captured by participants wearing AR glasses. We design a hardware-based data acquisition system and processing pipeline, achieving sub-millisecond temporal synchronization across views, coupled with accurate pose annotations. Experiment validation demonstrates the practical utility and effectiveness of our dataset for free-viewpoint video (FVV) applications, establishing MultiEgo as a foundational resource for advancing multi-view egocentric dynamic scene reconstruction research. |
| title | MultiEgo: A Multi-View Egocentric Video Dataset for 4D Scene Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.11301 |