High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits

Xiaoyong Shen, Hongyun Gao, Xin Tao, Chao Zhou, Jiaya Jia

ICCV 2017

doi:10.1109/ICCV.2017.353 /iccv/2017/shen2017iccv-highquality/

Abstract

Estimating correspondence between two images and extracting the foreground object are two challenges in computer vision. With dual-lens smart phones, such as iPhone 7Plus and Huawei P9, coming into the market, two images of slightly different views provide us new information to unify the two topics. We propose a joint method to tackle them simultaneously via a joint fully connected conditional random field (CRF) framework. The regional correspondence is used to handle textureless regions in matching and make our CRF system computationally efficient. Our method is evaluated over 2,000 new image pairs, and produces promising results on challenging portrait images.

PDF ICCV Semantic Scholar

Cite

Text

Shen et al. "High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits." International Conference on Computer Vision, 2017. doi:10.1109/ICCV.2017.353

Markdown

[Shen et al. "High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits." International Conference on Computer Vision, 2017.](https://mlanthology.org/iccv/2017/shen2017iccv-highquality/) doi:10.1109/ICCV.2017.353

BibTeX

@inproceedings{shen2017iccv-highquality,
  title     = {{High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits}},
  author    = {Shen, Xiaoyong and Gao, Hongyun and Tao, Xin and Zhou, Chao and Jia, Jiaya},
  booktitle = {International Conference on Computer Vision},
  year      = {2017},
  doi       = {10.1109/ICCV.2017.353},
  url       = {https://mlanthology.org/iccv/2017/shen2017iccv-highquality/}
}