Currently, digital avatars can be created manually using human images as reference. Systems such as Bitmoji are excellent producers of detailed avatar designs, with hundreds of choices for customization. A supervised learning model could be trained to generate avatars automatically, but the hundreds of possible options create difficulty in securing non-noisy data to train a model. As a solution, we train a model to produce avatars from human images using tag-based annotations. This method provides better annotator agreement, leading to less noisy data and higher quality model predictions. Our contribution is an application of tag-based annotation to train a model for avatar face creation. We design tags for 3 different facial facial features offered by Bitmoji, and train a model using tag-based annotation to predict the nose.
@article{arxiv.2308.12642,
title = {Tag-Based Annotation for Avatar Face Creation},
author = {An Ngo and Daniel Phelps and Derrick Lai and Thanyared Wong and Lucas Mathias and Anish Shivamurthy and Mustafa Ajmal and Minghao Liu and James Davis},
journal= {arXiv preprint arXiv:2308.12642},
year = {2023}
}