Controllable Style Transfer via Test-time Training of Implicit Neural Representation
This work addresses style transfer for image processing applications, offering improved control and efficiency, though it appears incremental as it builds on existing INR methods.
The authors tackled the problem of controllable style transfer by proposing a test-time training framework using Implicit Neural Representation, which allows pixel-wise control and resolution adjustment without further optimization after a single test-time training session.
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.