Total Selfie: Generating Full-Body Selfies
Abstract
We present a method to generate full-body selfies from photographs originally taken at arms length. Because self-captured photos are typically taken close up they have limited field of view and exaggerated perspective that distorts facial shapes. We instead seek to generate the photo some one else would take of you from a few feet away. Our approach takes as input four selfies of your face and body a background image and generates a full-body selfie in a desired target pose. We introduce a novel diffusion-based approach to combine all of this information into high-quality well-composed photos of you with the desired pose and background.
Cite
Text
Chen et al. "Total Selfie: Generating Full-Body Selfies." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.00640Markdown
[Chen et al. "Total Selfie: Generating Full-Body Selfies." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/chen2024cvpr-total/) doi:10.1109/CVPR52733.2024.00640BibTeX
@inproceedings{chen2024cvpr-total,
title = {{Total Selfie: Generating Full-Body Selfies}},
author = {Chen, Bowei and Curless, Brian and Kemelmacher-Shlizerman, Ira and Seitz, Steven M.},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {6701-6711},
doi = {10.1109/CVPR52733.2024.00640},
url = {https://mlanthology.org/cvpr/2024/chen2024cvpr-total/}
}