# Hypernetwork functional image representation

## TL;DR

This paper introduces a novel image representation method using hypernetworks that generate neural network weights for continuous, high-resolution image reconstruction and manipulation, demonstrating competitive super-resolution results.

## Contribution

It proposes a hypernetwork-based functional image representation that allows continuous image inspection and manipulation, a new approach in image modeling.

## Key findings

- Achieved super-resolution results comparable to existing methods.
- Enabled continuous image inspection and arbitrary resolution scaling.
- Demonstrated properties similar to generative models through interpolation.

## Abstract

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.