We propose a controllable style transfer framework based on Implicit Neural Representation that pixel-wisely controls the stylized output via test-time training. Unlike traditional image optimization methods that often suffer from unstable convergence and learning-based methods that require intensive training and have limited generalization ability, we present a model optimization framework that optimizes the neural networks during test-time with explicit loss functions for style transfer. After being test-time trained once, thanks to the flexibility of the INR-based model, our framework can precisely control the stylized images in a pixel-wise manner and freely adjust image resolution without further optimization or training. We demonstrate several applications.
@article{arxiv.2210.07762,
title = {Controllable Style Transfer via Test-time Training of Implicit Neural Representation},
author = {Sunwoo Kim and Youngjo Min and Younghun Jung and Seungryong Kim},
journal= {arXiv preprint arXiv:2210.07762},
year = {2022}
}