High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a lightweight training framework that significantly improves detail and texture fidelity in ultra-high-resolution (2K-4K) image synthesis. LWD introduces a novel, frequency-aware masking strategy derived from wavelet energy maps, which dynamically focuses the training process on detail-rich regions of the latent space. This is complemented by a scale-consistent VAE objective to ensure high spectral fidelity. The primary advantage of our approach is its efficiency: LWD requires no architectural modifications and adds zero additional cost during inference, making it a practical solution for scaling existing models. Across multiple strong baselines, LWD consistently improves perceptual quality and FID scores, demonstrating the power of signal-driven supervision as a principled and efficient path toward high-resolution generative modeling. The code is available at https://github.com/LuigiSigillo/LatentWaveletDiffusion
Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Institute of Automation, CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院智能感知与计算研究中心、模式识别国家重点实验室、自动化研究所、脑科学与智能技术卓越创新中心）；University of Chinese Academy of Sciences（中国科学院大学）
Age synthesis is a challenging task due to the complicated and non-linear transformation in human aging process. Aging information is usually reflected in local facial parts, such as wrinkles at the eye corners. However, these local facial parts contribute less in previous GAN based methods for age synthesis. To address this issue, we propose a Wavelet-domain Global and Local Consistent Age Generative Adversarial Network (WaveletGLCA-GAN), in which one global specific network and three local specific networks are integrated together to capture both global topology information and local texture…
WFM: 3D Wavelet Flow Matching for Ultrafast Multi-Modal MRI Synthesis
Department of Computer Science, Stanford University（斯坦福大学计算机科学系）；Machine and Hybrid Intelligence Lab, Feinberg School of Medicine, Northwestern University（北western大学费因伯格医学院机器与混合智能实验室）
本文提出WFM方法，通过学习基于小波空间条件均值的直接流，实现高效多模态MRI合成，单模型在BraTS 2024上达到26.8 dB PSNR和0.94 SSIM，速度比扩散模型快250-1000倍。
We provide a new model for texture synthesis based on a multiscale, multilayer feature extractor. Within the model, textures are represented by a set of statistics computed from ReLU wavelet coefficients at different layers, scales and orientations. A new image is synthesized by matching the target statistics via an iterative projection algorithm. We explain the necessity of the different types of pre-defined wavelet filters used in our model and the advantages of multilayer structures for image synthesis. We demonstrate the power of our model by generating samples of high quality textures and…
Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Synthesis with Modality and Metadata Conditioning
Department of Psychology & Neuroscience, Auckland University of Technology（心理学与神经科学系，奥克兰技术大学）；Department of Psychiatry, University of Melbourne（精神病学系，墨尔本大学）
Imperial College London（帝国理工学院）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）
Ovarian cancer is the most lethal gynaecological malignancy. The disease is most commonly asymptomatic at its early stages and its diagnosis relies on expert evaluation of transvaginal ultrasound images. Ultrasound is the first-line imaging modality for characterising adnexal masses, it requires significant expertise and its analysis is subjective and labour-intensive, therefore open to error. Hence, automating processes to facilitate and standardise the evaluation of scans is desired in clinical practice. Using supervised learning, we have demonstrated that segmentation of adnexal masses is p…
The Cyprus Institute（塞浦路斯研究所）；National and Kapodistrian University of Athens（雅典国立卡波季斯特里安大学）
In recent years, considerable advancements have been made in the area of Generative Adversarial Networks (GANs), particularly with the advent of style-based architectures that address many key shortcomings - both in terms of modeling capabilities and network interpretability. Despite these improvements, the adoption of such approaches in the domain of satellite imagery is not straightforward. Typical vision datasets used in generative tasks are well-aligned and annotated, and exhibit limited variability. In contrast, satellite imagery exhibits great spatial and spectral variability, wide prese…
Fetal brain magnetic resonance imaging (MRI) offers exquisite images of the developing brain but is not suitable for second-trimester anomaly screening, for which ultrasound (US) is employed. Although expert sonographers are adept at reading US images, MR images which closely resemble anatomical images are much easier for non-experts to interpret. Thus in this paper we propose to generate MR-like images directly from clinical US images. In medical image analysis such a capability is potentially useful as well, for instance for automatic US-MRI registration and fusion. The proposed model is end…
Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
State Key Laboratory of Complex and Critical Software Environment（复杂与关键软件环境国家重点实验室）；Beihang University（北京航空航天大学）；School of Computer Science and Engineering（计算机科学与工程学院）
Rutgers University（罗格斯大学）；Rutgers Cancer Institute of New Jersey（罗格斯大学新泽西癌症研究所）；Rutgers Robert Wood Johnson Medical School（罗格斯大学罗伯特·伍德·约翰逊医学院）；Johns Hopkins University（约翰斯·霍普金斯大学）
With the success of deep learning-based methods applied in medical image analysis, convolutional neural networks (CNNs) have been investigated for classifying liver disease from ultrasound (US) data. However, the scarcity of available large-scale labeled US data has hindered the success of CNNs for classifying liver disease from US data. In this work, we propose a novel generative adversarial network (GAN) architecture for realistic diseased and healthy liver US image synthesis. We adopt the concept of stacking to synthesize realistic liver US data. Quantitative and qualitative evaluation is p…
Shenzhen University（深圳大学）；Shenzhen RayShape Medical Technology Co., Ltd（深圳瑞影医疗科技有限公司）；Huizhou Central People’s Hospital（惠州市中心人民医院）
Ultrasound (US) is widely used for its advantages of real-time imaging, radiation-free and portability. In clinical practice, analysis and diagnosis often rely on US sequences rather than a single image to obtain dynamic anatomical information. This is challenging for novices to learn because practicing with adequate videos from patients is clinically unpractical. In this paper, we propose a novel framework to synthesize high-fidelity US videos. Specifically, the synthesis videos are generated by animating source content images based on the motion of given driving videos. Our highlights are th…
UltraG-Ray: Physics-Based Gaussian Ray Casting for Novel Ultrasound View Synthesis
Chair for Computer Aided Medical Procedures (CAMP), Technical University of Munich（慕尼黑工业大学计算机辅助医疗程序教席）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
Massachusetts Institute of Technology（麻省理工学院）；University of Toronto（多伦多大学）
In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development. Building on the recent success of graph neural networks for learning molecular embeddings and flow-based models for image generation, we propose Mol2Image: a flow-based generative model for molecule to cell image synthesis. To generate cell features at different resolutions and scale to high-resolution images, we develop a novel multi-scale flow architecture based on a Haar wavelet image pyramid. To maximize the mutual information between …
UltraDfeGAN: Detail-Enhancing Generative Adversarial Networks for High-Fidelity Functional Ultrasound Synthesis
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Department of Information and Communication, Institute of Technology of Cambodia（柬埔寨技术学院信息与通信系）；Department of Telecommunication and Network Engineering, Institute of Technology of Cambodia（柬埔寨技术学院电信与网络工程系）
ENS, PSL University（巴黎高等师范学院，巴黎文理研究大学）；Université de Toulouse, INP, IRIT（图卢兹大学，图卢兹国立综合理工学院，图卢兹信息学研究所）；Collège de France（法兰西公学院）；Flatiron Institute（弗莱提荣研究所）
State-of-the-art maximum entropy models for texture synthesis are built from statistics relying on image representations defined by convolutional neural networks (CNN). Such representations capture rich structures in texture images, outperforming wavelet-based representations in this regard. However, conversely to neural networks, wavelets offer meaningful representations, as they are known to detect structures at multiple scales (e.g. edges) in images. In this work, we propose a family of statistics built upon non-linear wavelet based representations, that can be viewed as a particular instan…
Ultrasound Image Synthesis Using Generative AI for Lung Ultrasound Detection
Johns Hopkins University（约翰斯·霍普金斯大学）；Philips Ultrasound（飞利浦超声）；Columbia University Vagelos College of Physicians and Surgeons（哥伦比亚大学瓦格洛斯内科医生与外科医生学院）；MedStar Washington Hospital Center（MedStar华盛顿医院中心）；Yale University School of Medicine（耶鲁大学医学院）
Korea University（高丽大学）；Netmarble Corporation（网石公司）
Although recent works on neural vocoder have improved the quality of synthesized audio, there still exists a gap between generated and ground-truth audio in frequency space. This difference leads to spectral artifacts such as hissing noise or reverberation, and thus degrades the sample quality. In this paper, we propose Fre-GAN which achieves frequency-consistent audio synthesis with highly improved generation quality. Specifically, we first present resolution-connected generator and resolution-wise discriminators, which help learn various scales of spectral distributions over multiple frequen…
3D Wavelet Latent Diffusion Model for Whole-Body MR-to-CT Modality Translation
School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）；School of Information Science and Technology, ShanghaiTech University（上海交通大学信息科学与技术学院）；Shanghai United Imaging Healthcare Co., Ltd.（上海联影医疗科技有限公司）；Department of Radiology and Biomedical Imaging, Yale University（耶鲁大学放射科与生物医学成像系）；Department of Applied Mathematics & Statistics and Department of Computer Science, Stony Brook University（石溪大学应用数学与统计系和计算机科学系）
Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation
State Key Laboratory of Complex and Critical Software Environment（复杂与关键软件环境国家重点实验室）；School of Computer Science and Engineering（计算机科学与工程学院）；Beihang University（北京航空航天大学）
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-the-art methods depend on a huge amount of labeled data and cannot be applied in an unpaired setting. On the other hand, generic unpaired image-to-image translation frameworks underperform in comparison, because they color-code semantic layouts and feed them to traditional convolutional networks, which then learn correspondences in appearance instead of semantic content. In this …
Recently, the reference functions for the synthesis and analysis of the autostereoscopic multiview and integral images in three-dimensional displays we introduced. In the current paper, we propose the wavelets to analyze such images. The wavelets are built on the reference functions as on the scaling functions of the wavelet analysis. The continuous wavelet transform was successfully applied to the testing wireframe binary objects. The restored locations correspond to the structure of the testing wireframe binary objects.
Improving Anomaly Detection with Foundation-Model Synthesis and Wavelet-Domain Attention
organization= School of Aeronautics；Astronautics , addressline= Zhejiang University , city= Hangzhou , postcode= 310027 , country= China；organization= School of Computer Science；organization= Ningbo Innovation Center , addressline= Zhejiang University , city= Ningbo , country= China；organization= Department of Automation , addressline= Tsinghua University , city= Beijing , postcode= 100084 , country= China；organization= College of Information Science \& Electronic Engineering , addressline= Zhejiang University , city= Hangzhou , postcode= 310027 , country= China
New Horizon College of Engineering（新视野工程学院）；Government Engineering College（政府工程学院）；University of Mysore（迈索尔大学）
Periodicity of a texture is one of the important visual characteristics and is often used as a measure for textural discrimination at the structural level. Knowledge about periodicity of a texture is very essential in the field of texture synthesis and texture compression and also in the design of frieze and wall papers. In this paper, we propose a method of periodicity extraction from noisy images based on superposition of distance matching function (DMF) and wavelet decomposition without de-noising the test images. Overall DMFs are subjected to single-level Haar wavelet decomposition to obta…
LifWavNet: Lifting Wavelet-based Network for Non-contact ECG Reconstruction from Radar
Rekhi Centre of Excellence for the Science of Happiness, IIT Kharagpur, India（幸福科学卓越中心，IIT哈里科普，印度）；Department of Electrical Engineering, IIT Kharagpur, India（电气工程系，IIT哈里科普，印度）；Department of Electronics and Electrical Communication Engineering, IIT Kharagpur, India（电子与电子通信工程系，IIT哈里科普，印度）
Velalar College of Engg.&Tech.（维拉拉尔工程技术学院）；PSG College of Technology（PSG理工学院）；Bannari Amman Institute of Technology（班纳里·阿曼理工学院）
A method for the design of Fast Haar wavelet for signal processing and image processing has been proposed. In the proposed work, the analysis bank and synthesis bank of Haar wavelet is modified by using polyphase structure. Finally, the Fast Haar wavelet was designed and it satisfies alias free and perfect reconstruction condition. Computational time and computational complexity is reduced in Fast Haar wavelet transform.
Implicit neural representations (INRs) have recently advanced numerous vision-related areas. INR performance depends strongly on the choice of the nonlinear activation function employed in its multilayer perceptron (MLP) network. A wide range of nonlinearities have been explored, but, unfortunately, current INRs designed to have high accuracy also suffer from poor robustness (to signal noise, parameter variation, etc.). Inspired by harmonic analysis, we develop a new, highly accurate and robust INR that does not exhibit this tradeoff. Wavelet Implicit neural REpresentation (WIRE) uses a contin…
Nanyang Technological University（南洋理工大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Wenzhou University（温州大学）；UCAS-Terminus AI Lab, UCAS（中国科学院大学-特米纳斯人工智能实验室，中国科学院大学）
In this work, we present an empirical study of DCGANs, including hyperparameter heuristics and image quality assessment, as a way to address the scarcity of datasets to investigate fetal head ultrasound. We present experiments to show the impact of different image resolutions, epochs, dataset size input, and learning rates for quality image assessment on four metrics: mutual information (MI), Fréchet inception distance (FID), peak-signal-to-noise ratio (PSNR), and local binary pattern vector (LBPv). The results show that FID and LBPv have stronger relationship with clinical image quality score…
Morphing is the process of combining two or more subjects in an image in order to create a new identity which contains features of both individuals. Morphed images can fool Facial Recognition Systems (FRS) into falsely accepting multiple people, leading to failures in national security. As morphed image synthesis becomes easier, it is vital to expand the research community's available data to help combat this dilemma. In this paper, we explore combination of two methods for morphed image generation, those of geometric transformation (warping and blending to create morphed images) and photometr…
