Hypernetwork functional image representation
This addresses image processing tasks like super-resolution by providing a continuous, generative-like representation, but it is incremental as it builds on hypernetwork and functional representation concepts.
The paper tackles image representation by introducing a functional approach where a hypernetwork generates weights for a target network that maps pixel positions to colors, enabling continuous image operations and multi-resolution inspection. They applied this to super-resolution, achieving results comparable to existing methods with a single model for various scaling factors.
Motivated by the human way of memorizing images we introduce their functional representation, where an image is represented by a neural network. For this purpose, we construct a hypernetwork which takes an image and returns weights to the target network, which maps point from the plane (representing positions of the pixel) into its corresponding color in the image. Since the obtained representation is continuous, one can easily inspect the image at various resolutions and perform on it arbitrary continuous operations. Moreover, by inspecting interpolations we show that such representation has some properties characteristic to generative models. To evaluate the proposed mechanism experimentally, we apply it to image super-resolution problem. Despite using a single model for various scaling factors, we obtained results comparable to existing super-resolution methods.