Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
This work presents TTFDNet, a transformer-based and transfer learning network for end-to-end depth estimation from single-frame fringe patterns in fringe projection profilometry. TTFDNet features a precise contour and coarse depth (PCCD) pre-processor, a global multi-dimensional fusion (GMDF) module and a progressive depth extractor (PDE). It utilizes transfer learning through fringe structure consistency evaluation (FSCE) to leverage the transformer's benefits even on a small dataset. Tested on 208 scenes, the model achieved a mean absolute error (MAE) of 0.00372 mm, outperforming Unet (0.03458 mm) models, PDE (0.01063 mm) and PCTNet (0.00518 mm). It demonstrated precise measurement capabilities with deviations of ~90 μm for a 25.4 mm radius ball and ~6 μm for a 20 mm thick metal part. Additionally, TTFDNet showed excellent generalization and robustness in dynamic reconstruction and varied imaging conditions, making it appropriate for practical applications in manufacturing, automation and computer vision.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11280829 | PMC |
| http://dx.doi.org/10.3390/s24144733 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Acceptability and effectiveness of empathy-based provider training and community-level awareness activities on self-injectable contraceptive use in Niger, Lagos, and Oyo States, Nigeria: a mixed methods program evaluation.
BMC Womens Health
September 2025
Society for Family Health-Nigeria, Abuja, Nigeria.
Background: Interventions aimed to increase healthcare provider empathy and capacity to deliver person-centered care have been shown to improve healthcare seeking and outcomes. In the context of self-injectable contraception, empathetic counseling and coaching may be promising approaches for addressing "fear of the needle" among clients interested in using subcutaneous depot medroxyprogesterone (DMPA-SC). In Nigeria, the Delivering Innovation in Self-Care (DISC) project developed and evaluated an empathy-based in-service training and supportive supervision intervention for public sector family (FP) planning providers implemented in conjunction with community-based mobilization.
View Article and Find Full Text PDFSingle camera estimation of microswimmer depth with a convolutional network.
J R Soc Interface
September 2025
Institute of Intelligent Systems and Robotics, Sorbonne Université, Paris, Île-de-France, France.
A number of techniques have been developed to measure the three-dimensional trajectories of protists, which require special experimental set-ups, such as a pair of orthogonal cameras. On the other hand, machine learning techniques have been used to estimate the vertical position of spherical particles from the defocus pattern, but they require the acquisition of a labelled dataset with finely spaced vertical positions. Here, we describe a simple way to make a dataset of images labelled with vertical position from a single 5 min movie, based on a tilted slide set-up.
View Article and Find Full Text PDFHIPSTR: highest independent posterior subtree reconstruction in TreeAnnotator X.
Bioinformatics
September 2025
Institute of Ecology and Evolution, University of Edinburgh, Edinburgh, United Kingdom.
Summary: In Bayesian phylogenetic and phylodynamic studies it is common to summarise the posterior distribution of trees with a time-calibrated summary phylogeny. While the maximum clade credibility (MCC) tree is often used for this purpose, we here show that a novel summary tree method-the highest independent posterior subtree reconstruction, or HIPSTR-contains consistently higher supported clades over MCC. We also provide faster computational routines for estimating both summary trees in an updated version of TreeAnnotator X, an open-source software program that summarizes the information from a sample of trees and returns many helpful statistics such as individual clade credibilities contained in the summary tree.
View Article and Find Full Text PDFDirected message passing neural networks enhanced graph convolutional learning for accurate polymer density prediction.
J Chem Phys
September 2025
National Synchrotron Radiation Laboratory, State Key Laboratory of Advanced Glass Materials, Anhui Provincial Engineering Research Center for Advanced Functional Polymer Films, University of Science and Technology of China, Hefei, Anhui 230029, China.
Polymer density is a critical factor influencing material performance and industrial applications, and it can be tailored by modifying the chemical structure of repeating units. Traditional polymer density characterization methods rely heavily on domain expertise; however, the vast chemical space comprising over one million potential polymer structures makes conventional experimental screening inefficient and costly. In this study, we proposed a machine learning framework for polymer density prediction, rigorously evaluating four models: neural networks (NNs), random forest (RF), XGBoost, and graph convolutional neural networks (GCNNs).
View Article and Find Full Text PDFEvolution of Motor and Nonmotor Characteristics in an Idiopathic/Isolated REM Sleep Behavior Disorder Cohort.
Neurology
October 2025
Montreal Neurological Institute-Hospital, McGill University, Montreal, Canada.
Background And Objectives: Years before diagnosis of Parkinson disease (PD), dementia with Lewy bodies (DLB), or multiple system atrophy (MSA), mild prodromal manifestations can be detected. Longitudinal follow-up of people with prodromal synucleinopathy, particularly idiopathic/isolated REM sleep behavior disorder (iRBD), enables in-depth clinical phenotyping of early disease, which could facilitate stratification for clinical trials, provide the definition of appropriate end points, or predict phenoconversion more precisely. The aim of this study was to update and expand on previous studies assessing clinical evolution from iRBD to clinically diagnosed disease, up to 14 years before diagnosis.
View Article and Find Full Text PDF