In Fringe Projection Profilometry (FPP), achieving robust and accurate 3D reconstruction with a limited number of fringe patterns remains a challenge in structured light 3D imaging. Conventional methods require a set of fringe images, but using only one or two patterns complicates phase recovery and unwrapping. In this study, we introduce SFNet, a symmetric fusion network that transforms two fringe images into an absolute phase. To enhance output reliability, Our framework predicts refined phases by incorporating information from fringe images of a different frequency than those used as input. This allows us to achieve high accuracy with just two images. Comparative experiments and ablation studies validate the effectiveness of our proposed method. The dataset and code are publicly accessible on our project page https://wonhoe-kim.github.io/SFNet.
Self-Supervised Dual-Frequency Phase Decomposition for Single-Shot Composite Fringe Projection Profilometry
Department of Mechanical Engineering, Yonsei University（延世大学机械工程系）；Yonsei Institute for Embodied Intelligence, Yonsei University（延世大学具身智能研究所）；Meta Reality Labs
PSNet: a deep learning model based digital phase shifting algorithm from a single fringe image
National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, College of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）
Deep Learning-enabled Spatial Phase Unwrapping for 3D Measurement
Sichuan University（四川大学）；State Key Laboratory of Oral Diseases（口腔疾病国家重点实验室）；National Clinical Research Center for Oral Diseases（国家口腔疾病临床医学研究中心）；West China Hospital of Stomatology, Sichuan University（四川大学华西口腔医院）
Novel Light Field Imaging Device with Enhanced Light Collection for Cold Atom Clouds
Stanford University（斯坦福大学）；SLAC National Accelerator Laboratory（SLAC国家加速器实验室）
我们提出了一个光场成像系统，捕获多个视图的对象与Single Shot。该系统被设计为通过接受比具有相等景深的传统镜头更大的光立体角来最大化总光收集。这是通过使用镜子填充虚拟对象的平面并充分利用可用的视场和景深来实现的。仿真结果表明，该设计能够对尺寸为$\mathcal{O}$（1 mm $^3$）的物体进行单次断层扫描，重建从任何单个视角孤立地不可访问的三维（3D）分布和特征。特别是，对于原子干涉实验中使用的原子云，该系统可以重建尺寸为$\mathcal{O}$（100 $μ$ m）的3D条纹图案。我们还用3D打印的原型展示了这个系统。该原型用于拍摄$\mathcal{O}$（1 mm $^{3}$）大小的物体的图像，并且在单次拍摄图像上运行的3D重建算法成功地重建了$\mathcal{O}$（100 $μ$ m）内部特征。该原型还表明，该系统可以使用3D打印技术构建，因此可以在需要增强光收集或3D重建的实验中快速且具有成本效益地部署。冷原子云的原子干涉成像是这种新型成像设备的关键应用，其中增强的光收集，高景深和3D断层重建可以提供新的处理来表征原子云。
Domain generalization in deep learning for contrast-enhanced imaging
Universitat de Barcelona（巴塞罗那大学）；Hospital de la Santa Creu i Sant Pau（圣十字圣保罗医院）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Hospital Universitari Vall d’Hebron（瓦尔德希伯伦大学医院）
WAVE-UNET: Wavelength based Image Reconstruction method using attention UNET for OCT images
Institute of Optical Materials and Technologies, Bulgarian Academy of Sciences（保加利亚科学院光学材料与技术研究所）；Faculty of Information Technology and Communication Sciences, Tampere University（坦佩雷大学信息技术与通信科学学院）；Electronics and Telecommunications Research Institute（电子与电信研究所）
Enhanced Deep Learning DeepFake Detection Integrating Handcrafted Features
Facephi Biometrics S.A.（Facephi 生物特征技术公司）；da/sec-Biometrics and Internet Security Research Group（生物特征与网络安全研究小组）；Internet Security Research Group（网络安全研究小组）
Opening the Black Box of Financial AI with CLEAR-Trade: A CLass-Enhanced Attentive Response Approach for Explaining and Visualizing Deep Learning-Driven Stock Market Prediction
University of Guelph（圭尔夫大学）；CIFAR（加拿大高等研究院）；Vector Institute（向量研究所）；University of Waterloo（滑铁卢大学）；Waterloo AI Institute（滑铁卢人工智能研究所）
