Total Selfie: Generating Full-Body Selfies

August 28, 2023 · Entered Twilight · 🏛 Computer Vision and Pattern Recognition

"No code URL or promise found in abstract"
"Code repo scraped from project page (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, CONTRIBUTING.md, LICENSE, README.md, configs, eval.py, hypernerf, notebooks, requirements.txt, setup.py, train.py

Authors Bowei Chen, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz arXiv ID 2308.14740 Category cs.CV: Computer Vision Cross-listed cs.GR, cs.LG Citations 8 Venue Computer Vision and Pattern Recognition Repository https://github.com/google/hypernerf ⭐ 958 Last Checked 2 months ago

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.