Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metrics

Authors: Hiromu Yakura, Yuki Koyama, Masataka Goto

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments with various third-party tools, such as Instagram and Blender, show that our framework can effectively leverage deep learning techniques for computational design support.
Researcher Affiliation Academia 1University of Tsukuba, Japan 2National Institute of Advanced Industrial Science and Technology (AIST), Japan
Pseudocode No The paper describes the framework conceptually and visually through diagrams, but it does not include any formal pseudocode or algorithm blocks.
Open Source Code No The paper mentions using publicly available models from GitHub but does not state that the authors are releasing their own source code for the methodology presented in this paper.
Open Datasets Yes We randomly selected ten pairs of the original and reference selfies from the dataset of Gu et al. [2019] and prepared imitating selfies by using our framework.
Dataset Splits No The paper focuses on leveraging pretrained models and conducting subjective evaluations. It does not describe any specific training/validation dataset splits used for training models in this work, as the models they employ are already pretrained.
Hardware Specification No The paper mentions using an "Android emulator" for experiments but does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments or the pretrained models.
Software Dependencies No The paper mentions using "UIAutomator", "Optuna", "Instagram", "SNOW", and "Blender", but it does not provide specific version numbers for these software components or any other underlying libraries/frameworks.
Experiment Setup Yes Then we used Optuna for 1,000 iterations to find parameters of the makeup transformations, such as lip color and eyebrows, that minimize the distance to the reference selfie in the latent space.