Single View Metrology in the Wild

Abstract

Most 3D reconstruction methods may only recover scene properties up to a global scale ambiguity. We present a novel approach to single view metrology that can recover the absolute scale of a scene represented by 3D heights of objects or camera height above the ground as well as camera parameters of orientation and field of view, using just a monocular image acquired in unconstrained condition. Our method relies on data-driven priors learned by a deep network specifically designed to imbibe weakly supervised constraints from the interplay of the unknown camera with 3D entities such as object heights, through estimation of bounding box projections. We leverage categorical priors for objects such as humans or cars that commonly occur in natural images, as references for scale estimation. We demonstrate state-of-the-art qualitative and quantitative results on several datasets as well as applications including virtual object insertion. Furthermore, the perceptual quality of our outputs is validated by a user study.

Cite

Text

Zhu et al. "Single View Metrology in the Wild." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58621-8_19

Markdown

[Zhu et al. "Single View Metrology in the Wild." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/zhu2020eccv-single/) doi:10.1007/978-3-030-58621-8_19

BibTeX

@inproceedings{zhu2020eccv-single,
  title     = {{Single View Metrology in the Wild}},
  author    = {Zhu, Rui and Yang, Xingyi and Hold-Geoffroy, Yannick and Perazzi, Federico and Eisenmann, Jonathan and Sunkavalli, Kalyan and Chandraker, Manmohan},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58621-8_19},
  url       = {https://mlanthology.org/eccv/2020/zhu2020eccv-single/}
}