A Real World Dataset for Multi-View 3D Reconstruction

Rakesh Shrestha, Siqi Hu, Minghao Gou, Ziyuan Liu, Ping Tan

ECCV 2022

doi:10.1007/978-3-031-20074-8_4 /eccv/2022/shrestha2022eccv-real/

Abstract

We present a dataset of 371 3D models of everyday tabletop objects along with their 320,000 real world RGB and depth images. Accurate annotations of camera poses and object poses for each image are performed in a semi-automated fashion to facilitate the use of the dataset for myriad 3D applications like shape reconstruction, object pose estimation, shape retrieval etc. We primarily focus on learned multi-view 3D reconstruction due to the lack of appropriate real world benchmark for the task and demonstrate that our dataset can fill that gap. The entire annotated dataset along with the source code for the annotation tools and evaluation baselines will be made publicly available. Keywords: Dataset, Multi-view 3D reconstruction

PDF ECCV Semantic Scholar

Cite

Text

Shrestha et al. "A Real World Dataset for Multi-View 3D Reconstruction." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-20074-8_4

Markdown

[Shrestha et al. "A Real World Dataset for Multi-View 3D Reconstruction." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/shrestha2022eccv-real/) doi:10.1007/978-3-031-20074-8_4

BibTeX

@inproceedings{shrestha2022eccv-real,
  title     = {{A Real World Dataset for Multi-View 3D Reconstruction}},
  author    = {Shrestha, Rakesh and Hu, Siqi and Gou, Minghao and Liu, Ziyuan and Tan, Ping},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2022},
  doi       = {10.1007/978-3-031-20074-8_4},
  url       = {https://mlanthology.org/eccv/2022/shrestha2022eccv-real/}
}