Shinichiro Omachi

Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu et al.

Image Super-Resolution (SR) is essential for a wide range of computer vision and image processing tasks. Investigating infrared (IR) image (or thermal images) super-resolution is a continuing concern within the development of deep learning. This survey aims to provide a comprehensive perspective of IR image super-resolution, including its applications, hardware imaging system dilemmas, and taxonomy of image processing methodologies. In addition, the datasets and evaluation metrics in IR image super-resolution tasks are also discussed. Furthermore, the deficiencies in current technologies and possible promising directions for the community to explore are highlighted. To cope with the rapid development in this field, we intend to regularly update the relevant excellent work at https://github.com/yongsongH/Infrared_Image_SR_Survey.

Yongsong Huang, Qingzhong Wang, Shinichiro Omachi

In this paper, we present a medical AttentIon Denoising Super Resolution Generative Adversarial Network (AID-SRGAN) for diographic image super-resolution. First, we present a medical practical degradation model that considers various degradation factors beyond downsampling. To the best of our knowledge, this is the first composite degradation model proposed for radiographic images. Furthermore, we propose AID-SRGAN, which can simultaneously denoise and generate high-resolution (HR) radiographs. In this model, we introduce an attention mechanism into the denoising module to make it more robust to complicated degradation. Finally, the SR module reconstructs the HR radiographs using the "clean" low-resolution (LR) radiographs. In addition, we propose a separate-joint training approach to train the model, and extensive experiments are conducted to show that the proposed method is superior to its counterparts. e.g., our proposed method achieves $31.90$ of PSNR with a scale factor of $4 \times$, which is $7.05 \%$ higher than that obtained by recent work, SPSR [16]. Our dataset and code will be made available at: https://github.com/yongsongH/AIDSRGAN-MICCAI2022.

Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu et al.

Recent efforts have explored leveraging visible light images to enrich texture details in infrared (IR) super-resolution. However, this direct adaptation approach often becomes a double-edged sword, as it improves texture at the cost of introducing noise and blurring artifacts. To address these challenges, we propose the Target-oriented Domain Adaptation SRGAN (DASRGAN), an innovative framework specifically engineered for robust IR super-resolution model adaptation. DASRGAN operates on the synergy of two key components: 1) Texture-Oriented Adaptation (TOA) to refine texture details meticulously, and 2) Noise-Oriented Adaptation (NOA), dedicated to minimizing noise transfer. Specifically, TOA uniquely integrates a specialized discriminator, incorporating a prior extraction branch, and employs a Sobel-guided adversarial loss to align texture distributions effectively. Concurrently, NOA utilizes a noise adversarial loss to distinctly separate the generative and Gaussian noise pattern distributions during adversarial training. Our extensive experiments confirm DASRGAN's superiority. Comparative analyses against leading methods across multiple benchmarks and upsampling factors reveal that DASRGAN sets new state-of-the-art performance standards. Code are available at \url{https://github.com/yongsongH/DASRGAN}.

Zhengmi Tang, Tomo Miyazaki, Shinichiro Omachi

Scene-text image synthesis techniques that aim to naturally compose text instances on background scene images are very appealing for training deep neural networks due to their ability to provide accurate and comprehensive annotation information. Prior studies have explored generating synthetic text images on two-dimensional and three-dimensional surfaces using rules derived from real-world observations. Some of these studies have proposed generating scene-text images through learning; however, owing to the absence of a suitable training dataset, unsupervised frameworks have been explored to learn from existing real-world data, which might not yield reliable performance. To ease this dilemma and facilitate research on learning-based scene text synthesis, we introduce DecompST, a real-world dataset prepared from some public benchmarks, containing three types of annotations: quadrilateral-level BBoxes, stroke-level text masks, and text-erased images. Leveraging the DecompST dataset, we propose a Learning-Based Text Synthesis engine (LBTS) that includes a text location proposal network (TLPNet) and a text appearance adaptation network (TAANet). TLPNet first predicts the suitable regions for text embedding, after which TAANet adaptively adjusts the geometry and color of the text instance to match the background context. After training, those networks can be integrated and utilized to generate the synthetic dataset for scene text analysis tasks. Comprehensive experiments were conducted to validate the effectiveness of the proposed LBTS along with existing methods, and the experimental results indicate the proposed LBTS can generate better pretraining data for scene text detectors.

Shoma Iwai, Atsuki Osanai, Shunsuke Kitada et al.

Layout generation is a task to synthesize a harmonious layout with elements characterized by attributes such as category, position, and size. Human designers experiment with the placement and modification of elements to create aesthetic layouts, however, we observed that current discrete diffusion models (DDMs) struggle to correct inharmonious layouts after they have been generated. In this paper, we first provide novel insights into layout sticking phenomenon in DDMs and then propose a simple yet effective layout-assessment module Layout-Corrector, which works in conjunction with existing DDMs to address the layout sticking problem. We present a learning-based module capable of identifying inharmonious elements within layouts, considering overall layout harmony characterized by complex composition. During the generation process, Layout-Corrector evaluates the correctness of each token in the generated layout, reinitializing those with low scores to the ungenerated state. The DDM then uses the high-scored tokens as clues to regenerate the harmonized tokens. Layout-Corrector, tested on common benchmarks, consistently boosts layout-generation performance when in conjunction with various state-of-the-art DDMs. Furthermore, our extensive analysis demonstrates that the Layout-Corrector (1) successfully identifies erroneous tokens, (2) facilitates control over the fidelity-diversity trade-off, and (3) significantly mitigates the performance drop associated with fast sampling.

Ajda Lampe, Julija Stopar, Deepak Kumar Jain et al.

Recent developments in deep generative models have opened up a wide range of opportunities for image synthesis, leading to significant changes in various creative fields, including the fashion industry. While numerous methods have been proposed to benefit buyers, particularly in virtual try-on applications, there has been relatively less focus on facilitating fast prototyping for designers and customers seeking to order new designs. To address this gap, we introduce DiCTI (Diffusion-based Clothing Designer via Text-guided Input), a straightforward yet highly effective approach that allows designers to quickly visualize fashion-related ideas using text inputs only. Given an image of a person and a description of the desired garments as input, DiCTI automatically generates multiple high-resolution, photorealistic images that capture the expressed semantics. By leveraging a powerful diffusion-based inpainting model conditioned on text inputs, DiCTI is able to synthesize convincing, high-quality images with varied clothing designs that viably follow the provided text descriptions, while being able to process very diverse and challenging inputs, captured in completely unconstrained settings. We evaluate DiCTI in comprehensive experiments on two different datasets (VITON-HD and Fashionpedia) and in comparison to the state-of-the-art (SoTa). The results of our experiments show that DiCTI convincingly outperforms the SoTA competitor in generating higher quality images with more elaborate garments and superior text prompt adherence, both according to standard quantitative evaluation measures and human ratings, generated as part of a user study.

Weiwei Ma, Xiaobing Yu, Peijie Qiu et al.

In clinical practice, medical segmentation datasets are often limited and heterogeneous, with variations in modalities, protocols, and anatomical targets across institutions. Existing deep learning models struggle to jointly learn from such diverse data, often sacrificing either generalization or domain-specific knowledge. To overcome these challenges, we propose a joint training method called Universal Harmonization (U-Harmony), which can be integrated into deep learning-based architectures with a domain-gated head, enabling a single segmentation model to learn from heterogeneous datasets simultaneously. By integrating U-Harmony, our approach sequentially normalizes and then denormalizes feature distributions to mitigate domain-specific variations while preserving original dataset-specific knowledge. More appealingly, our framework also supports universal modality adaptation, allowing the seamless learning of new imaging modalities and anatomical classes. Extensive experiments on cross-institutional brain lesion datasets demonstrate the effectiveness of our approach, establishing a new benchmark for robust and adaptable 3D medical image segmentation models in real-world clinical settings.

Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu et al.

Infrared image super-resolution demands long-range dependency modeling and multi-scale feature extraction to address challenges such as homogeneous backgrounds, weak edges, and sparse textures. While Mamba-based state-space models (SSMs) excel in global dependency modeling with linear complexity, their block-wise processing disrupts spatial consistency, limiting their effectiveness for IR image reconstruction. We propose IRSRMamba, a novel framework integrating wavelet transform feature modulation for multi-scale adaptation and an SSMs-based semantic consistency loss to restore fragmented contextual information. This design enhances global-local feature fusion, structural coherence, and fine-detail preservation while mitigating block-induced artifacts. Experiments on benchmark datasets demonstrate that IRSRMamba outperforms state-of-the-art methods in PSNR, SSIM, and perceptual quality. This work establishes Mamba-based architectures as a promising direction for high-fidelity IR image enhancement. Code are available at https://github.com/yongsongH/IRSRMamba.

Juan Wang, Yasutomo Kawanishi, Tomo Miyazaki et al.

3D instance segmentation is an important task for real-world applications. To avoid costly manual annotations, existing methods have explored generating pseudo labels by transferring 2D masks from foundation models to 3D. However, this approach is often suboptimal since the video frames are processed independently. This causes inconsistent segmentation granularity and conflicting 3D pseudo labels, which degrades the accuracy of final segmentation. To address this, we introduce a Granularity-Consistent automatic 2D Mask Tracking approach that maintains temporal correspondences across frames, eliminating conflicting pseudo labels. Combined with a three-stage curriculum learning framework, our approach progressively trains from fragmented single-view data to unified multi-view annotations, ultimately globally coherent full-scene supervision. This structured learning pipeline enables the model to progressively expose to pseudo-labels of increasing consistency. Thus, we can robustly distill a consistent 3D representation from initially fragmented and contradictory 2D priors. Experimental results demonstrated that our method effectively generated consistent and accurate 3D segmentations. Furthermore, the proposed method achieved state-of-the-art results on standard benchmarks and open-vocabulary ability.

Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu et al.

Infrared Image Super-Resolution (IRSR) is challenged by the low contrast and sparse textures of infrared data, requiring robust long-range modeling to maintain global coherence. While State-Space Models like Mamba offer proficiency in modeling long-range dependencies for this task, their inherent 1D causal scanning mechanism fragments the global context of 2D images, hindering fine-detail restoration. To address this, we propose Global Phase and Spectral Prompt-guided Mamba (GPSMamba), a framework that synergizes architectural guidance with non-causal supervision. First, our Adaptive Semantic-Frequency State Space Module (ASF-SSM) injects a fused semantic-frequency prompt directly into the Mamba block, integrating non-local context to guide reconstruction. Then, a novel Thermal-Spectral Attention and Phase Consistency Loss provides explicit, non-causal supervision to enforce global structural and spectral fidelity. By combining these two innovations, our work presents a systematic strategy to mitigate the limitations of causal modeling. Extensive experiments demonstrate that GPSMamba achieves state-of-the-art performance, validating our approach as a powerful new paradigm for infrared image restoration. Code is available at https://github.com/yongsongH/GPSMamba.

Taïga Gonçalves, Tomo Miyazaki, Shinichiro Omachi

Multi-targeted adversarial attacks aim to mislead classifiers toward specific target classes using a single perturbation generator with a conditional input specifying the desired target class. Existing methods face two key limitations: (1) a single generator supports only a limited number of predefined target classes, and (2) it requires access to the victim model's training data to learn target class semantics. This dependency raises data leakage concerns in practical black-box scenarios where the training data is typically private. To address these limitations, we propose a novel Cross-Domain Multi-Targeted Attack (CD-MTA) that can generate perturbations toward arbitrary target classes, even those that do not exist in the attacker's training data. CD-MTA is trained on a single public dataset but can perform targeted attacks on black-box models trained on different datasets with disjoint and unknown class sets. Our method requires only a single example image that visually represents the desired target class, without relying its label, class distribution or pretrained embeddings. We achieve this through a Feature Injection Module (FIM) and class-agnostic objectives which guide the generator to extract transferable, fine-grained features from the target image without inferring class semantics. Experiments on ImageNet and seven additional datasets show that CD-MTA outperforms existing multi-targeted attack methods on unseen target classes in black-box and cross-domain scenarios. The code is available at https://github.com/tgoncalv/CD-MTA.

Yaohou Fan, Qingzhong Wang, Yongsong Huang et al.

Current visual text generation models struggle with the trade-off between text accuracy and overall image coherence. We find that achieving high text accuracy can reduce aesthetic quality and instruction-following capability. Although reinforcement learning approaches can alleviate the problem through aligning with multiple rewards, they are often unstable for text generation, as existing approaches normally optimize multiple rewards in a weighted-sum way. In addition, it is difficult to balance the weight of each reward. Moreover, reinforcement learning requires a set of training instructions. A large number of prompts require more training time and computing resources, while a small set leads to poor performance. Hence, how to select the prompts for efficient training is an unsolved problem. In this study, we propose Pareto-Optimal Curriculum Alignment (POCA), a framework that addresses this issue as a multi-objective problem by: 1) identifying the Pareto-optimal set to avoid simple scalarization and 2) designing an adaptive curriculum alignment strategy to manage a learning sequence of a multi-reward dataset using automatic difficulty assessment, which is crucial for optimal convergence as RL methods explore in a limited data environment. In synergy, POCA finds the Pareto-optimal set in a unified reward space, which eliminates inconsistent signals to find the best trade-off solution from different rewards under an easy-to-hard optimization landscape. The experimental results show that POCA significantly improves all metrics such as CLIP, HPS scores and sentence accuracy.

Yongsong Huang, Tzu-Hsuan Peng, Tomo Miyazaki et al.

Low-light image super-resolution (LLSR) is a challenging task due to the coupled degradation of low resolution and poor illumination. To address this, we propose the Guided Texture and Feature Modulation Network (GTFMN), a novel framework that decouples the LLSR task into two sub-problems: illumination estimation and texture restoration. First, our network employs a dedicated Illumination Stream whose purpose is to predict a spatially varying illumination map that accurately captures lighting distribution. Further, this map is utilized as an explicit guide within our novel Illumination Guided Modulation Block (IGM Block) to dynamically modulate features in the Texture Stream. This mechanism achieves spatially adaptive restoration, enabling the network to intensify enhancement in poorly lit regions while preserving details in well-exposed areas. Extensive experiments demonstrate that GTFMN achieves the best performance among competing methods on the OmniNormal5 and OmniNormal15 datasets, outperforming them in both quantitative metrics and visual quality.

Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu et al.

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.

Zhengmi Tang, Yuto Mitsui, Tomo Miyazaki et al.

Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven illumination, irregular layout, occlusion, and degradation, resulting in performance disparities when handling complex real-world images. Recent self-supervised learning techniques, notably contrastive learning and masked image modeling (MIM), narrow this domain gap by exploiting unlabeled real text images. This study first analyzes the original Masked AutoEncoder (MAE) and observes that random patch masking predominantly captures low-level textural features but misses high-level contextual representations. To fully exploit the high-level contextual representations, we introduce random blockwise and span masking in the text recognition task. These strategies can mask the continuous image patches and completely remove some characters, forcing the model to infer relationships among characters within a word. Our Multi-Masking Strategy (MMS) integrates random patch, blockwise, and span masking into the MIM frame, which jointly learns low and high-level textual representations. After fine-tuning with real data, MMS outperforms the state-of-the-art self-supervised methods in various text-related tasks, including text recognition, segmentation, and text-image super-resolution.

Shohei Uchigasaki, Tomo Miyazaki, Shinichiro Omachi

Image compression is a fundamental technology for Internet communication engineering. However, a high compression rate with general methods may degrade images, resulting in unreadable texts. In this paper, we propose an image compression method for maintaining text quality. We developed a scene text image quality assessment model to assess text quality in compressed images. The assessment model iteratively searches for the best-compressed image holding high-quality text. Objective and subjective results showed that the proposed method was superior to existing methods. Furthermore, the proposed assessment model outperformed other deep-learning regression models.

Zhengmi Tang, Tomo Miyazaki, Yoshihiro Sugaya et al.

Scene text erasing, which replaces text regions with reasonable content in natural images, has drawn significant attention in the computer vision community in recent years. There are two potential subtasks in scene text erasing: text detection and image inpainting. Both subtasks require considerable data to achieve better performance; however, the lack of a large-scale real-world scene-text removal dataset does not allow existing methods to realize their potential. To compensate for the lack of pairwise real-world data, we made considerable use of synthetic text after additional enhancement and subsequently trained 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 cropped text image to maintain more background content for better inpainting results. This model can partially erase text instances in a scene image with a bounding box or work with an existing scene-text detector for automatic scene text erasing. The experimental results from the qualitative 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 they are trained on real-world data.

Shoma Iwai, Tomo Miyazaki, Yoshihiro Sugaya et al.

We propose a GAN-based image compression method working at extremely low bitrates below 0.1bpp. Most existing learned image compression methods suffer from blur at extremely low bitrates. Although GAN can help to reconstruct sharp images, there are two drawbacks. First, GAN makes training unstable. Second, the reconstructions often contain unpleasing noise or artifacts. To address both of the drawbacks, our method adopts two-stage training and network interpolation. The two-stage training is effective to stabilize the training. Moreover, the network interpolation utilizes the models in both stages and reduces undesirable noise and artifacts, while maintaining important edges. Hence, we can control the trade-off between perceptual quality and fidelity without re-training models. The experimental results show that our model can reconstruct high quality images. Furthermore, our user study confirms that our reconstructions are preferable to state-of-the-art GAN-based image compression model. The code will be available.

Huy Manh Nguyen, Tomo Miyazaki, Yoshihiro Sugaya et al.

Visual-semantic embedding aims to learn a joint embedding space where related video and sentence instances are located close to each other. Most existing methods put instances in a single embedding space. However, they struggle to embed instances due to the difficulty of matching visual dynamics in videos to textual features in sentences. A single space is not enough to accommodate various videos and sentences. In this paper, we propose a novel framework that maps instances into multiple individual embedding spaces so that we can capture multiple relationships between instances, leading to compelling video retrieval. We propose to produce a final similarity between instances by fusing similarities measured in each embedding space using a weighted sum strategy. We determine the weights according to a sentence. Therefore, we can flexibly emphasize an embedding space. We conducted sentence-to-video retrieval experiments on a benchmark dataset. The proposed method achieved superior performance, and the results are competitive to state-of-the-art methods. These experimental results demonstrated the effectiveness of the proposed multiple embedding approach compared to existing methods.

Tomo Miyazaki, Shinichiro Omachi

This paper presents a novel method for structural data recognition using a large number of graph models. In general, prevalent methods for structural data recognition have two shortcomings: 1) Only a single model is used to capture structural variation. 2) Naive recognition methods are used, such as the nearest neighbor method. In this paper, we propose strengthening the recognition performance of these models as well as their ability to capture structural variation. The proposed method constructs a large number of graph models and trains decision trees using the models. This paper makes two main contributions. The first is a novel graph model that can quickly perform calculations, which allows us to construct several models in a feasible amount of time. The second contribution is a novel approach to structural data recognition: graph model boosting. Comprehensive structural variations can be captured with a large number of graph models constructed in a boosting framework, and a sophisticated classifier can be formed by aggregating the decision trees. Consequently, we can carry out structural data recognition with powerful recognition capability in the face of comprehensive structural variation. The experiments shows that the proposed method achieves impressive results and outperforms existing methods on datasets of IAM graph database repository.

Tomo Miyazaki, Tatsunori Tsuchiya, Yoshihiro Sugaya et al.

This paper addresses the automatic generation of a typographic font from a subset of characters. Specifically, we use a subset of a typographic font to extrapolate additional characters. Consequently, we obtain a complete font containing a number of characters sufficient for daily use. The automated generation of Japanese fonts is in high demand because a Japanese font requires over 1,000 characters. Unfortunately, professional typographers create most fonts, resulting in significant financial and time investments for font generation. The proposed method can be a great aid for font creation because designers do not need to create the majority of the characters for a new font. The proposed method uses strokes from given samples for font generation. The strokes, from which we construct characters, are extracted by exploiting a character skeleton dataset. This study makes three main contributions: a novel method of extracting strokes from characters, which is applicable to both standard fonts and their variations; a fully automated approach for constructing characters; and a selection method for sample characters. We demonstrate our proposed method by generating 2,965 characters in 47 fonts. Objective and subjective evaluations verify that the generated characters are similar to handmade characters.