Edge-oriented Implicit Neural Representation with Channel Tuning
This work addresses a specific limitation in image processing for applications requiring high-quality edge reconstruction, representing an incremental improvement over existing methods.
The paper tackled the problem of restoring clear edges in implicit neural representations for images by proposing a Gradient Magnitude Adjustment algorithm and an Edge-oriented Representation Network (EoREN) with a Channel-tuning module, resulting in improved reconstruction of complex signals with quantitative demonstrations.
Implicit neural representation, which expresses an image as a continuous function rather than a discrete grid form, is widely used for image processing. Despite its outperforming results, there are still remaining limitations on restoring clear shapes of a given signal such as the edges of an image. In this paper, we propose Gradient Magnitude Adjustment algorithm which calculates the gradient of an image for training the implicit representation. In addition, we propose Edge-oriented Representation Network (EoREN) that can reconstruct the image with clear edges by fitting gradient information (Edge-oriented module). Furthermore, we add Channel-tuning module to adjust the distribution of given signals so that it solves a chronic problem of fitting gradients. By separating backpropagation paths of the two modules, EoREN can learn true color of the image without hindering the role for gradients. We qualitatively show that our model can reconstruct complex signals and demonstrate general reconstruction ability of our model with quantitative results.