When zooming between dual cameras on a mobile, noticeable jumps in geometric content and image color occur in the preview, inevitably affecting the user's zoom experience. In this work, we introduce a new task, ie, dual-camera smooth zoom (DCSZ) to achieve a smooth zoom preview. The frame interpolation (FI) technique is a potential solution but struggles with ground-truth collection. To address the issue, we suggest a data factory solution where continuous virtual cameras are assembled to generate DCSZ data by rendering reconstructed 3D models of the scene. In particular, we propose a novel dual-camera smooth zoom Gaussian Splatting (ZoomGS), where a camera-specific encoding is introduced to construct a specific 3D model for each virtual camera. With the proposed data factory, we construct a synthetic dataset for DCSZ, and we utilize it to fine-tune FI models. In addition, we collect real-world dual-zoom images without ground-truth for evaluation. Extensive experiments are conducted with multiple FI methods. The results show that the fine-tuned FI models achieve a significant performance improvement over the original ones on DCSZ task. The datasets, codes, and pre-trained models will are available at https://github.com/ZcsrenlongZ/ZoomGS.
An Object-Centered Data Acquisition Method for 3D Gaussian Splatting using Mobile Phones
School of Electronics and Information, Northwestern Polytechnical University(电子信息学院,西北工业大学);College of Engineering, Xi'an International University(工程学院,西安国际大学)
Mobile Phone Based Vehicle License Plate Recognition for Road Policing
TCS Innovation Labs - Mumbai(塔塔咨询服务公司孟买创新实验室)
一般来说,交通警察通过车辆牌照来识别车辆。车牌识别在智能交通管理系统中有着广泛的应用.全球的安全形势,特别是印度的安全形势,要求为交通警察配备一个系统,使他们能够即时获得车辆的详细信息。该系统应该易于使用,应该是移动的,并工作24 x 7。在本文中,我们描述了一个基于手机,客户端-服务器架构,车牌识别系统。虽然我们使用最先进的图像处理和模式识别算法调整为印度的条件,自动识别非统一的车牌,主要贡献是在创建一个端到端的可用的解决方案。客户端应用程序在移动终端上运行,并且可以访问车辆信息数据库的服务器应用程序被集中托管。该解决方案能够捕获由手机摄像头捕获的牌照图像并将其传递到服务器;在服务器上识别牌照号码;然后将与牌照相关联的数据立即发送回移动终端。我们详细描述了端到端的系统架构。该系统的工作原型已在实验室环境中实现。
Fast Deep Matting for Portrait Animation on Mobile Phone
National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);North China University of Technology(北方工业大学)
University of California, Los Angeles(加州大学洛杉矶分校);California NanoSystems Institute (CNSI), University of California, Los Angeles(加州大学洛杉矶分校加州纳米系统研究所);David Geffen School of Medicine, University of California, Los Angeles(加州大学洛杉矶分校大卫·格芬医学院)
National Research University Higher School of Economics(国立研究大学高等经济学院);Yandex School of Data Analysis(Yandex数据分析学院);Moscow Institute of Physics and Technology(莫斯科物理技术学院);Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究院);University of California, Davis(加利福尼亚大学戴维斯分校);University of California, Irvine(加利福尼亚大学欧文分校);Yale University(耶鲁大学)
Deep learning model trained on mobile phone-acquired frozen section images effectively detects basal cell carcinoma
Meriti, Inc(梅里蒂公司);Carolinas Dermatology and Plastic Surgery(卡罗莱纳皮肤科与整形外科);Dahl-Chase Pathology Associates(达尔-蔡斯病理联合机构);Beaumont Health System(博蒙特医疗系统)
背景:使用冰冻切片评估基底细胞癌的边缘是术中病理会诊的常见任务。虽然通常是直接的,但在组织切片上确定是否存在基底细胞癌有时可能具有挑战性。我们探索在手机获取的冷冻切片图像上训练的深度学习模型是否可以为未来的部署提供足够的性能。材料与方法:使用手机采集了1241张用于基底细胞癌边缘状态的冷冻切片图像。照片以100倍放大率(10倍物镜)拍摄。图像从4032 x 3024像素分辨率缩小到576 x 432像素分辨率。使用具有Xception主干的语义分割算法Deeplab V3进行模型训练。结果如下:该模型使用图像作为输入,并产生相同维度的预测的二维黑白输出;确定为基底细胞癌的区域在黑色背景中以白色显示。白色像素数超过像素总数0.5%的任何输出被认为是基底细胞癌阳性。在测试集上,该模型在像素级上实现了0.99的接收者操作曲线和0.97的精确度-召回率曲线的曲线下面积。在玻片水平上的分类准确率为96%。结论:用手机图像训练的深度学习模型显示出令人满意的性能特征,因此证明了作为手机应用程序部署以实时的辅助冰冻切片解释的潜力。