In geometry processing, symmetry is a universal type of high-level structural information of 3D models and benefits many geometry processing tasks including shape segmentation, alignment, matching, and completion. Thus it is an important problem to analyze various symmetry forms of 3D shapes. Planar reflective symmetry is the most fundamental one. Traditional methods based on spatial sampling can be time-consuming and may not be able to identify all the symmetry planes. In this article, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape. Our framework trains an unsupervised 3D convolutional neural network to extract global model features and then outputs possible global symmetry parameters, where input shapes are represented using voxels. We introduce a dedicated symmetry distance loss along with a regularization loss to avoid generating duplicated symmetry planes. Our network can also identify generalized cylinders by predicting their rotation axes. We further provide a method to remove invalid and duplicated planes and axes. We demonstrate that our method is able to produce reliable and accurate results. Our neural network based method is hundreds of times faster than the state-of-the-art methods, which are based on sampling. Our method is also robust even with noisy or incomplete input surfaces.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TVCG.2020.3003823DOI Listing

Publication Analysis

Top Keywords

planar reflective
12
reflective symmetry
12
symmetry
9
geometry processing
8
methods based
8
symmetry planes
8
neural network
8
prs-net planar
4
symmetry detection
4
detection net
4

Similar Publications

High-throughput measurement of cellular traction forces at the nanoscale remains a significant challenge in mechanobiology, limiting our understanding of how cells interact with their microenvironment. Here, we present a novel technique for fabricating protein nanopatterns in standard multiwell microplate formats (96/384-wells), enabling the high-throughput quantification of cellular forces using DNA tension gauge tethers (TGTs) amplified by CRISPR-Cas12a. Our method employs sparse colloidal lithography to create nanopatterned surfaces with feature sizes ranging from sub 100 to 800 nm on transparent, planar, and fully PEGylated substrates.

View Article and Find Full Text PDF

L-Shaped Coplanar Strip Dipole Antenna Sensor for Adulteration Detection.

Sensors (Basel)

January 2025

Department of Civil Environmental and Mechanical Engineering, University of Trento, 38123 Trento, Italy.

The present study proposes an L-shaped coplanar strip dipole antenna for sensing the presence of adulterants in liquid food samples. The proposed antenna dimensions are optimized using ANSYS HFSS, and a prototype is fabricated and validated. The sensing region is optimized based on the current distribution and measured reflection coefficients.

View Article and Find Full Text PDF

Research on Dry Coupling Technology in the Ultrasonic Non-Destructive Testing of Concrete.

Micromachines (Basel)

January 2025

College of Mechanical & Electrical Engineering, Central South University, Changsha 410083, China.

In the health monitoring and safety assessments of concrete structures, ultrasonic non-destructive testing (NDT) technology has become an indispensable tool due to its non-destructive nature, efficiency, and precision. However, when used in inspecting irregular concrete surfaces, traditional planar ultrasonic transducers often encounter energy loss and signal attenuation induced by poor interface coupling, which significantly reduces the accuracy and reliability of the test results. To address this problem, this article proposes a point-contact dry coupling ultrasonic transducer solution, which enables efficient acquisition of ultrasonic signals within concrete without the need for couplants.

View Article and Find Full Text PDF

Background: Splenic stiffness is a potential imaging marker of portal hypertension. Normative spleen stiffness values are needed to define diagnostic thresholds.

Objective: To report stiffness measurements of the spleen in healthy children undergoing liver magnetic resonance (MR) elastography across MRI vendors and field strengths.

View Article and Find Full Text PDF

Functional magnetic resonance imaging (fMRI) of the spinal cord is relevant for studying sensation, movement, and autonomic function. Preprocessing of spinal cord fMRI data involves segmentation of the spinal cord on gradient-echo echo planar imaging (EPI) images. Current automated segmentation methods do not work well on these data, due to the low spatial resolution, susceptibility artifacts causing distortions and signal drop-out, ghosting, and motion-related artifacts.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!