A Generative AI Framework to Predict Cardiomyocyte Contraction Function From Single Static Images
A single static hiPSC‐cardiomyocyte image is fed into a U‐Net‐GAN framework, which directly predicts a pixel‐resolved contraction heatmap without time‐lapse imaging. StyleGAN2‐generated synthetic cell–heatmap pairs augment training, improving prediction fidelity (SSIM = 0.84).
Andrew Kowalczewski +5 more
wiley +1 more source
A Deep Learning-Based Framework for Offline Robotic Weld Path Generation Using a Single Top-View RGB-D Image. [PDF]
Lee D, Ko B, Park T, Yoon JW, Park H.
europepmc +1 more source
How much material loss is concealed beneath a layer of corrosion products? This proof‐of‐concept study demonstrates how concealed volume loss is inferred from the optical appearance and as‐exposed surface topography of AZ31 corrosion imprints. By predicting postcleaning depth maps, a multimodal U‐Net model estimates hidden volume loss without chromic ...
Lars Dammann +8 more
wiley +1 more source
CoFUSE-EPWNet: Cross-Modal Consistency Fusion for RGB-D Express Packaging Waste Detection in Green Campus Management. [PDF]
Yu F, Gong G, Li L.
europepmc +1 more source
A laser pointer‐guided robotic grasping method for arbitrary objects based on promptable segment anything model and force‐closure analysis is presented. Grasp generation methods based on force‐closure analysis can calculate the optimal grasps for objects through their appearances. However, the limited visual perception ability makes robots difficult to
Yan Liu +5 more
wiley +1 more source
Enhanced RGB-D feature extraction for 6D pose estimation. [PDF]
Zhang H, Tong J, Wei L, Zhang H, Chen J.
europepmc +1 more source
Temperature‐Tunable Cholesteric Liquid Crystal Optical Combiners for Extended Reality Applications
Recent advancements in extended reality highlight their potential to enhance traditional displays like liquid crystal displays and organic light‐emitting diode screens. This article introduces an innovative cholesteric liquid crystal‐based optical combiner for head‐mounted displays, enabling seamless transitions between augmented reality, virtual ...
Yuanjie Xia +6 more
wiley +1 more source
Budget-Aware Rescue Routing for Low-Overlap Indoor RGB-D Point Cloud Registration. [PDF]
Lin Y +5 more
europepmc +1 more source
A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis
A novel hybrid transfer learning approach for brain tumor classification achieves 99.47% accuracy using magnetic resonance imaging (MRI) images. By combining image preprocessing, ensemble deep learning, and explainable artificial intelligence (XAI) techniques like gradient‐weighted class activation mapping and SHapley Additive exPlanations (SHAP), the ...
Sadia Islam Tonni +11 more
wiley +1 more source
Synchrony Vision: An RGB-D Sensor-Based System for Real-Time Monitoring and Event-Level Analysis of Interpersonal Motion Synchrony. [PDF]
Kwon J.
europepmc +1 more source

