Towards Arbitrary-scale Histopathology Image Super-resolution: An Efficient Dual-branch Framework based on Implicit Self-texture Enhancement

TL;DR

This paper introduces a novel dual-branch framework with self-texture enhancement for arbitrary-scale super-resolution of pathology images, overcoming limitations of existing models and outperforming current algorithms.

Contribution

It presents the first method for arbitrary-scale super-resolution in pathology images using an efficient dual-branch network with self-texture enhancement.

Findings

Outperforms existing fixed-scale and arbitrary-scale algorithms

Effective in preserving fine-grained textures in pathology images

Achieves superior results on public datasets

Abstract

Existing super-resolution models for pathology images can only work in fixed integer magnifications and have limited performance. Though implicit neural network-based methods have shown promising results in arbitrary-scale super-resolution of natural images, it is not effective to directly apply them in pathology images, because pathology images have special fine-grained image textures different from natural images. To address this challenge, we propose a dual-branch framework with an efficient self-texture enhancement mechanism for arbitrary-scale super-resolution of pathology images. Extensive experiments on two public datasets show that our method outperforms both existing fixed-scale and arbitrary-scale algorithms. To the best of our knowledge, this is the first work to achieve arbitrary-scale super-resolution in the field of pathology images. Codes will be available.