Total Selfie: Generating Full-Body Selfies

Bowei Chen, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 6701-6711

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.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Bowei and Curless, Brian and Kemelmacher-Shlizerman, Ira and Seitz, Steven M.}, title = {Total Selfie: Generating Full-Body Selfies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6701-6711} }