Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended semantics of the associated text prompts. We examine cross-attention layers in diffusion models and observe a propensity for these layers to disproportionately focus on certain tokens during the generation process, thereby undermining semantic fidelity. To address the issue of dominant attention, we introduce attention regulation, a computation-efficient on-the-fly optimization approach at inference time to align attention maps with the input text prompt. Notably, our method requires no additional training or fine-tuning and serves as a plug-in module on a model. Hence, the generation capacity of the original model is fully preserved. We compare our approach with alternative approaches across various datasets, evaluation metrics, and diffusion models. Experiment results show that our method consistently outperforms other baselines, yielding images that more faithfully reflect the desired concepts with reduced computation overhead. Code is available at https://github.com/YaNgZhAnG-V5/attention_regulation.
Foreground Focus: Enhancing Coherence and Fidelity in Camouflaged Image Generation
Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）；National Yang Ming Chiao Tung University（国立阳明交通大学）；Jilin University（吉林大学）；MediaTek（联发科）；National Taiwan University（国立台湾大学）
Enhancing Image Generation Fidelity via Progressive Prompts
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Tsinghua University（清华大学）；Peking university（北京大学）；EaseUS（易我科技）；The Hong Kong University of Science and Technology（香港科技大学）
Digital Surgery（数字外科公司）；Kasetsart University（农业大学）
Surgical simulation is an increasingly important element of surgical education. Using simulation can be a means to address some of the significant challenges in developing surgical skills with limited time and resources. The photo-realistic fidelity of simulations is a key feature that can improve the experience and transfer ratio of trainees. In this paper, we demonstrate how we can enhance the visual fidelity of existing surgical simulation by performing style transfer of multi-class labels from real surgical video onto synthetic content. We demonstrate our approach on simulations of catarac…
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）
Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study
University of Peradeniya, Sri Lanka（斯里兰卡大学）；University of Maryland, College Park, USA（美国马里兰大学 College Park 分校）；Tulane University School of Medicine, USA（美国 Tulane 大学医学院）；Simula Research Laboratory, Norway（挪威 Simula 研究实验室）；SimulaMet, Norway（挪威 SimulaMet）
Enhancing Texture Generation with High-Fidelity Using Advanced Texture Priors
MetaApp AI Research（MetaApp AI研究院）；Zhengzhou University（郑州大学）；Beijing Institute of Technology（北京理工大学）；Beijing University of Technology（北京工业大学）；Northeastern University（东北大学）
Enhancing Scene Classification in Cloudy Image Scenarios: A Collaborative Transfer Method with Information Regulation Mechanism using Optical Cloud-Covered and SAR Remote Sensing Images
School of Geosciences and Info-Physics, Central South University（中南大学地球科学与信息物理学院）；Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente（特文特大学地球信息科学与地球观测学院）
NeuroGAN-3D: Enhancing Intrinsic Functional Brain Networks via High-Fidelity 3D Generative Super-Resolution
Georgia State University（佐治亚州立大学）；Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS)（神经影像与数据科学转化研究三机构中心（TReNDS））；Georgia Institute of Technology（佐治亚理工学院）；Emory University（埃默里大学）
Few-Shot Medical Image Segmentation with High-Fidelity Prototypes
University of Shanghai for Science and Technology（上海理工大学）；Universität Hamburg（汉堡大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Electronic Science and Technology of China（电子科技大学）；University of Surrey（萨里大学）
Semantic and Temporal Integration in Latent Diffusion Space for High-Fidelity Video Super-Resolution
Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China（图像通信与网络工程研究所，上海交通大学，上海，中国）；Tencent, Shanghai, China（腾讯，上海，中国）
