检索结果-内蒙古大学图书馆

Detail-Enhancing Framework for Reference-Based image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Zihan Xiong, Ziliang Tang, Hongying Yuan, Xiaobing Shanghai Institution of Micro-system and Information Technology University of Chinese Academy of Science China Computer Vision Laboratory Department of Electrical Engineering LiU Sweden School of Information Science and Technology Shanghai Tech University China

Recent years have witnessed the prosperity of reference-based image super-resolution (Ref-SR). By importing the high-resolution (HR) reference images into the single image super-resolution (SISR) approach, the ill-posed nature of this long-standing field has been alleviated with the assistance of texture transferred from reference images. Although the significant improvement in quantitative and qualitative results has verified the superiority of Ref-SR methods, the presence of misalignment before texture transfer indicates room for further performance improvement. Existing methods tend to neglect the significance of details in the context of comparison, therefore not fully leveraging the information contained within low-resolution (LR) images. In this paper, we propose a Detail-Enhancing Framework (DEF) for reference-based super-resolution, which introduces the diffusion model to generate and enhance the underlying detail in LR images. If corresponding parts are present in the reference image, our method can facilitate rigorous alignment. In cases where the reference image lacks corresponding parts, it ensures a fundamental improvement while avoiding the influence of the reference image. Extensive experiments demonstrate that our proposed method achieves superior visual results while maintaining comparable numerical outcomes. Copyright © 2024, The Authors. All rights reserved.

关键词： Textures

学校读者我要写书评

暂无评论

Triple Point Masking

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Liu, Jiaming Kong, Linghe Wu, Yue Gong, Maoguo Li, Hao Miao, Qiguang Ma, Wenping Qin, Can The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Technology Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The School of Electronic Engineering Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The College of Mathematics Science Inner Mongolia Normal University Hohhot010022 China The School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi’an710071 China The Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States

Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation. In this paper, we introduce a triple point masking scheme, named TPM, which serves as a scalable plug- and-play framework for MAE pre-training to achieve multi-mask learning for 3D point clouds. Specifically, we augment the baseline methods with two additional mask choices (i.e., medium mask and low mask) as our core insight is that the recovery process of an object can manifest in diverse ways. Previous high-masking schemes focus on capturing the global representation information but lack fine-grained recovery capabilities, so that the generated pre-training weights tend to play a limited role in the fine-tuning process. With the support of the proposed TPM, current methods can exhibit more flexible and accurate completion capabilities, enabling the potential autoencoder in the pre-training stage to consider multiple representations of a single 3D point cloud object. In addition, during the fine-tuning stage, an SVM-guided weight selection module is proposed to fill the encoder parameters for downstream networks with the optimal weight, maximizing linear accuracy and facilitating the acquisition of intricate representations for new objects. Extensive experimental results and theoretical analysis show that five baselines equipped with the proposed TPM achieve comprehensive performance improvements on various downstream tasks. © 2025 IEEE. All rights reserved.

关键词： 3D modeling

DAE-Former: Dual Attention-guided Efficient Transformer for Medical image Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Azad, Reza Arimond, René Aghdam, Ehsan Khodapanah Kazerouni, Amirhossein Merhof, Dorit Institute of Imaging and Computer Vision RWTH Aachen University Aachen Germany Department of Electrical Engineering Shahid Beheshti University Tehran Iran School of Electrical Engineering Iran University of Science and Technology Tehran Iran Institute of Image Analysis and Computer Vision Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from quadratic computational complexity with respect to the number of tokens. Many architectures attempt to reduce model complexity by limiting the self-attention mechanism to local regions or by redesigning the tokenization process. In this paper, we propose DAE-Former, a novel method that seeks to provide an alternative perspective by efficiently designing the self-attention mechanism. More specifically, we reformulate the self-attention mechanism to capture both spatial and channel relations across the whole feature dimension while staying computationally efficient. Furthermore, we redesign the skip connection path by including the cross-attention module to ensure the feature reusability and enhance the localization power. Our method outperforms state-of-the-art methods on multi-organ cardiac and skin lesion segmentation datasets without requiring pre-training weights. The code is publicly available at GitHub. © 2022, CC BY.

关键词： Reusability

LoMAE: Low-level vision Masked Autoencoders for Low-dose CT Denoising

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Dayang Xu, Yongshun Han, Shuo Wu, Zhan Zhou, Li Morovati, Bahareh Yu, Hengyong The Department of Electrical and Computer Engineering University of Massachusetts Lowell LowellMA01854 United States The Laboratory of Image Science and Technology Southeast University Nanjing210096 China The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China

Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance LDCT image quality. However, the success of such models relies on a large amount of paired noisy and clean images, which are often scarce in clinical settings. In the fields of computer vision and natural language processing, masked autoencoders (MAE) have been recognized as an effective label-free self-pretraining method for transformers, due to their exceptional feature representation ability. However, the original pretraining and fine-tuning design fails to work in low-level vision tasks like denoising. In response to this challenge, we redesign the classical encoder-decoder learning model and facilitate a simple yet effective low-level vision MAE, referred to as LoMAE, tailored to address the LDCT denoising problem. Moreover, we introduce an MAE-GradCAM method to shed light on the latent learning mechanisms of the MAE/LoMAE. Additionally, we explore the LoMAE’s robustness and generability across a variety of noise levels. Experiments results show that the proposed LoMAE can enhance the transformer’s denoising performance and greatly relieve the dependence on the ground truth clean data. It also demonstrates remarkable robustness and generalizability over a spectrum of noise levels. © 2023, CC BY.

关键词： image quality

Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report

学校读者我要写书评

暂无评论

Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challen...

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Conde, Marcos V. Kolmet, Manuel Seizinger, Tim Bishop, Tom E. Timofte, Radu Kong, Xiangyu Zhang, Dafeng Wu, Jinlong Wang, Fan Peng, Juewen Pan, Zhiyu Liu, Chengxin Luo, Xianrui Sun, Huiqiang Shen, Liao Cao, Zhiguo Xian, Ke Liu, Chaowei Chen, Zigeng Yang, Xingyi Liu, Songhua Jing, Yongcheng Mi, Michael Bi Wang, Xinchao Yang, Zhihao Lian, Wenyi Lai, Siyuan Zhang, Haichuan Hoang, Trung Yazdani, Amirsaeed Monga, Vishal Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Zhao, Yuxuan Chen, Baoliang Xu, Yiqing Niu, Jixiang Computer Vision Lab CAIDAS IFI University of Würzburg Germany Glass Imaging Inc. China Huazhong University of Science and Technology China Nanyang Technological University Singapore National University of Singapore Singapore University of Sydney Australia Huawei Uppsala University Sweden Department of Electrical Engineering Pennsylvania State University United States Department of Information Technology Uppsala University Sweden Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education Xidian University Xi'an China North China University of Technology China

ISBN: (纸本)9798350302493

We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational photography is to optimize the Bokeh effect itself, which is the aesthetic quality of the blur in out-of-focus areas of an image. Photographers create this aesthetic effect by benefiting from the lens optical *** aim of this work is to design a neural network capable of converting the the Bokeh effect of one lens to the effect of another lens without harming the sharp foreground regions in the image. For a given input image, knowing the target lens type, we render or transform the Bokeh effect accordingly to the lens properties. We build the BETD using two full-frame Sony cameras, and diverse lens *** the best of our knowledge, we are the first attempt to solve this novel task, and we provide the first BETD dataset and benchmark for it. The challenge had 99 registered participants. The submitted methods gauge the state-of-the-art in Bokeh effect rendering and transformation. © 2023 IEEE.

关键词： Color photography

Diagnostic Accuracy and Reliability of Deep Learning-Based Human Papillomavirus Status Prediction in Oropharyngeal Cancer

学校读者我要写书评

暂无评论

Diagnostic Accuracy and Reliability of Deep Learning-Based H...

International Conference on Medical Imaging and computer-Aided Diagnosis, MICAD 2022

作者： La Greca Saint-Esteven, Agustina Marchiori, Chiara Bogowicz, Marta Barranco-García, Javier Khodabakhshi, Zahra Konukoglu, Ender Riesterer, Oliver Balermpas, Panagiotis Hüllner, Martin Malossi, A. Cristiano I. Guckenberger, Matthias van Timmeren, Janita E. Tanadini-Lang, Stephanie Department of Radiation Oncology University Hospital Zurich and the University of Zurich Rämistrasse 100 Zurich8091 Switzerland Computer Vision Laboratory Department of Information Technology and Electrical Engineering ETH Zurich Sternwartstrasse 7 Zurich8092 Switzerland IBM Research Zurich Säumerstrasse 4 Rüschlikon8803 Switzerland Department of Nuclear Medicine University Hospital Zurich and the University of Zurich Rämistrasse 100 Zurich8091 Switzerland

ISBN: (纸本)9789811667749

Oropharyngeal cancer (OPC) patients with associated human papillomavirus (HPV) infection generally present more favorable outcomes than HPV-negative patients and, consequently, their treatment with radiation therapy may be potentially de-escalated. The diagnostic accuracy of a deep learning (DL) model to predict HPV status on computed tomography (CT) images was evaluated in this study, together with its ability to perform unsupervised heatmap-based localization of relevant regions in OPC and HPV infection, i.e., the primary tumor and lymph nodes, as a measure of its reliability. The dataset consisted of 767 patients from one internal and two public collections from The Cancer Imaging Archive and was split into training, validation and test sets using the ratio 60–20–20. images were resampled to a resolution of 2 mm3 and a sub-volume of 96 pixels3 was automatically cropped, which spanned from the nose until the start of the lungs. Models Genesis was fine-tuned for the classification task. Grad-CAM and Score-CAM were applied to the test subjects that belonged to the internal cohort (n = 24), and the overlap and Dice coefficients between the resulting heatmaps and the planning target volumes (PTVs) were calculated. Final train/validation/test area-under-the-curve (AUC) values of 0.9/0.87/0.87, accuracies of 0.83/0.82/0.79, and F1-scores of 0.83/0.79/0.74 were achieved. The reliability analysis showed an increased focus on dental artifacts in HPV-positive patients, whereas promising overlaps and moderate Dice coefficients with the PTVs were obtained for HPV-negative cases. These findings prove the necessity of performing reliability studies before a DL model is implemented in a real clinical setting, even if there is optimal diagnostic accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diseases

A Completely Blind Video Quality Evaluator

学校读者我要写书评

暂无评论

IEEE Signal Processing Letters 2022年 29卷 2228-2232页

作者： Qi Zheng Zhengzhong Tu Xiaoyang Zeng Alan C. Bovik Yibo Fan State Key Laboratory of ASIC & System College of Microelectronics Fudan University Shanghai China Laboratory for Image and Video Engineering (LIVE) Department of Electrical and Computer Engineering The University of Texas at Austin Austin TX USA

Automatic video quality assessment of user-generated content (UGC) has gained increased interest recently, due to the ubiquity of shared video clips uploaded and circulated on social media platforms across the globe. Most existing video quality models developed for this vast content are trained on large numbers of samples labeled during large-scale subjective studies, which are often fail to exhibit adequate generalization abilities on unseen data. Thus, it is also desirable to develop opinion-unaware, “completely blind” video quality models, that are free of training, yet can compete with existing learning-based models. Here we propose such a model called VIQE (VIdeo Quality Evaluator), which we designed based on a comprehensive analysis of patch- and frame-wise video statistics, as well as of space-time statistical regularities of videos. The statistical features desired from the analysis capture complementary predictive aspects of perceptual quality, which are aggregated to obtain final video quality scores. Extensive experiments on recent large-scale video quality databases demonstrate that VIQE is even competitive with state-of-the-art opinion-aware models. The source code is being made available at https://***/uniqzheng/VIQE .

关键词： Video recording Quality assessment Feature extraction Computational modeling Streaming media Distortion Distortion measurement

Extraordinary Quality Factors in Dual-Band Polarization-Insensitive QuasiBound States in the Continuum

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ghahremani, Maryam Zapata-Rodríguez, Carlos J. Photonics Research Laboratory Center of Excellence on Applied Electromagnetic Systems School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Department of Optics and Optometry and Vision Sciences Faculty of Physics University of Valencia Dr. Moliner 50 Burjassot46100 Spain

In this study, we investigate a novel "dimerized" dielectric metasurface featuring dual-mode resonances governed by symmetry-protected bound states in the continuum (BICs). The metasurface design offers advantages such as insensitivity to incident light polarization and exceptionally high quality factors exceeding 105 for low and moderate structural deviations from the monoatomic array. By introducing mastered perturbations in the metasurface via the Brillouin zone folding method, without reducing symmetry, we explore the behavior of symmetry-protected BIC states and their polarization-independent responses. Through numerical simulations and analysis, we demonstrate the superiority of Q factors for specific BIC-based resonances, leading to precise control over interaction behaviors and light engineering in both near and far fields. Our findings contribute to the understanding of BIC resonance interactions and offer insights into the design of high-performance sensing applications and meta-devices with enhanced functionalities. © 2024, CC BY-NC-ND.

关键词： Incident light

Metamaterial-induced-transparency engineering through quasi-bound states in the continuum by using dielectric cross-shaped trimers

学校读者我要写书评

暂无评论

arXiv 2024年

This study presents a novel approach to activate a narrowband transparency line within a reflecting broadband window in all-dielectric metasurfaces, in analogy to the electromagnetically-induced transparency effect, by means of a quasi-bound state in the continuum (qBIC). We demonstrate that the resonance overlapping of a bright mode and a qBIC-based nearly-dark mode with distinct Q-factor can be fully governed by a silicon trimer-based unit cell with broken-inversion-symmetry cross shape, thus providing the required response under normal incidence of a linearly-polarized light. Our analysis that is derived from the far-field multipolar decomposition and near-field electromagnetic distributions uncovers the main contributions of different multipoles on the qBIC resonance, with governing magnetic dipole and electric quadrupole terms supplied by distinct parts of the dielectric "molecule." The findings extracted from this research open up new avenues for the development of polarization-dependent technologies, with particular interest in its capabilities for sensing and biosensing. © 2024, CC BY-NC-ND.

关键词： Transparency