Precision 3D volume measurement of transparent adhesives via spectrally optimized line laser scanning and enhanced centroid extraction
Spectrally optimized line laser scanning combined with an enhanced centroid extraction algorithm enables precision volume measurement of transparent adhesives, overcoming the light-scattering artifacts that corrupt conventional laser profilometry.
Jan 1, 2025
Identifying frequency-domain operating deflection shapes and internal damage in structures using geometric vision method
This paper presents a geometric vision method for frequency-domain operating deflection shape sensing and internal damage identification, using RANSAC-based stereo calibration, stereo-temporal matching, ODS estimation, and wavelet-based damage localization.
Jan 1, 2025
Fast Shape Retrieval Based on Differential Chain Code Descriptor and Fuzzy Contour Matching
This work converts CAD contour matching into a differential chain-code sequence problem, then uses segmented fuzzy matching and SVD verification to retrieve similar shapes quickly and robustly under noise, scale changes, and partial contour deformation.
Jan 1, 2025
DeSC: Learning Deep Semantic Descriptor for NeRF Registration
DeSC learns deep semantic descriptors from NeRF's view-independent embedding space, combining local implicit photometric cues, graph aggregation, Transformer context, and density-aware photometric consistency for robust NeRF-to-NeRF registration.
Jan 1, 2025
VeinTr: Robust end-to-end full-hand vein identification with transformer
VeinTr is an end-to-end transformer model for full-hand vein biometric identification that captures global vein topology through self-attention, achieving robust recognition across imaging conditions and hand poses without manual feature engineering.
Oct 1, 2024
Segmentation-Driven Feature-Preserving Mesh Denoising
This paper proposes a segmentation-driven mesh denoising framework that partitions noisy triangle meshes with an edge-based region-growing operator, maps reliable regions back to the noisy input, and performs region-wise denoising to preserve sharp features.
Sep 1, 2024
Reconstruction of transparent objects using phase shifting profilometry based on diffusion models
Diffusion models are leveraged to reconstruct transparent object surfaces from phase-shifting profilometry data, learning to inpaint and denoise the corrupted fringe patterns caused by refraction and specular reflections.
Apr 1, 2024
Generative deep-learning-embedded asynchronous structured light for three-dimensional imaging
A generative deep learning model embedded in an asynchronous structured light system recovers high-fidelity 3D shape from temporally misaligned fringe captures, enabling real-time 3D imaging of dynamic scenes without hardware synchronisation.
Jan 1, 2024
Gap measurement method based on projection lines and convex analysis of 3D point clouds
A geometric method combining projection-line fitting and convex analysis on 3D point clouds precisely measures gap dimensions in assembled components, providing a robust alternative to contact gauging for automated industrial inspection.
Jan 1, 2024
A Point Cloud Contour Extraction Method based on Plane Segmentation
A method based on plane segmentation and dimensionality reduction for extracting incomplete and slow contour features of object point clouds is proposed.
Jan 1, 2024