Learn From Orientation Prior for Radiograph Super-Resolution: Orientation Operator Transformer

Background and objective: High-resolution radiographic images play a pivotal role in the early diagnosis and treatment of skeletal muscle-related diseases. It is promising to enhance image quality by introducing single-image super-resolution (SISR) model into the radiology image field. However, the conventional image pipeline, which can learn a mixed mapping between SR and denoising from the color space and inter-pixel patterns, poses a particular challenge for radiographic images with limited pattern features. To address this issue, this paper introduces a novel approach: Orientation Operator Transformer - $O^{2}$former. Methods: We incorporate an orientation operator in the encoder to enhance sensitivity to denoising mapping and to integrate orientation prior. Furthermore, we propose a multi-scale feature fusion strategy to amalgamate features captured by different receptive fields with the directional prior, thereby providing a more effective latent representation for the decoder. Based on these innovative components, we propose a transformer-based SISR model, i.e., $O^{2}$former, specifically designed for radiographic images. Results: The experimental results demonstrate that our method achieves the best or second-best performance in the objective metrics compared with the competitors at $\times 4$ upsampling factor. For qualitative, more objective details are observed to be recovered. Conclusions: In this study, we propose a novel framework called $O^{2}$former for radiological image super-resolution tasks, which improves the reconstruction model's performance by introducing an orientation operator and multi-scale feature fusion strategy. Our approach is promising to further promote the radiographic image enhancement field.

A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data

Scene-text image synthesis techniques aimed at naturally composing text instances on background scene images are very appealing for training deep neural networks because they can provide accurate and comprehensive annotation information. Prior studies have explored generating synthetic text images on two-dimensional and three-dimensional surfaces based on rules derived from real-world observations. Some of these studies have proposed generating scene-text images from learning; however, owing to the absence of a suitable training dataset, unsupervised frameworks have been explored to learn from existing real-world data, which may not result in a robust performance. To ease this dilemma and facilitate research on learning-based scene text synthesis, we propose DecompST, a real-world dataset prepared using public benchmarks, with three types of annotations: quadrilateral-level BBoxes, stroke-level text masks, and text-erased images. Using the DecompST dataset, we propose an image synthesis engine that includes a text location proposal network (TLPNet) and a text appearance adaptation network (TAANet). TLPNet first predicts the suitable regions for text embedding. TAANet then adaptively changes the geometry and color of the text instance according to the context of the background. Our comprehensive experiments verified the effectiveness of the proposed method for generating pretraining data for scene text detectors.

Stroke-Based Scene Text Erasing Using Synthetic Data

Scene text erasing, which replaces text regions with reasonable content in natural images, has drawn attention in the computer vision community in recent years. There are two potential subtasks in scene text erasing: text detection and image inpainting. Either sub-task requires considerable data to achieve better performance; however, the lack of a large-scale real-world scene-text removal dataset allows the existing methods to not work in full strength. To avoid the limitation of the lack of pairwise real-world data, we enhance and make full use of the synthetic text and consequently train our model only on the dataset generated by the improved synthetic text engine. Our proposed network contains a stroke mask prediction module and background inpainting module that can extract the text stroke as a relatively small hole from the text image patch to maintain more background content for better inpainting results. This model can partially erase text instances in a scene image with a bounding box provided or work with an existing scene text detector for automatic scene text erasing. The experimental results of qualitative evaluation and quantitative evaluation on the SCUT-Syn, ICDAR2013, and SCUT-EnsText datasets demonstrate that our method significantly outperforms existing state-of-the-art methods even when trained on real-world data.