Abstract

Retrieving 3D models by adopting hand-drawn sketches to be the input has turned out to be a popular study topic. Most current methods are based on manually selected features and the best view produced for 3D model calculations. However, there are many problems with these methods such as distortion. For the purpose of dealing with such issues, this paper proposes a novel feature representation method to select the projection view and adapt the maxout network to the extended Siamese network architecture. In addition, the strategy is able to handle the over-fitting issue of convolutional neural networks (CNN) and mitigate the discrepancies between the 3D shape domain and the sketch. A pre-trained AlexNet was used to sketch the extract features. For 3D shapes, multiple 2D views were compiled into compact feature vectors using pre-trained multi-view CNNs. Then the Siamese convolutional neural networks were learnt for transforming the two domains’ original characteristics into nonlinear feature space, which mitigated the domain discrepancy and kept the discriminations. Two large data sets were used for experiments, and the experimental results show that the method is superior to the prior art methods in accuracy.

Highlights

  • The 3D model retrieval based on sketch pays attention to the retrieval of related 3D patterns by adopting the sketches to be the input [1,2,3]

  • We propose to study the feature representations for 3D patterns and sketches, which ignore the predicament of the most outstanding view selection; Two original Siamese convolutional neural networks were used for dealing with the overfitting issue and to explore similar points successfully in and across the domains

  • This paper considers a strategy based on convolutional neural networks (CNN), which is considered to be a deep learning strategy and a kind of feedforward neural network that contains convolutional computation and has a deep structure

Read more

Summary

A Novel Sketch-Based Three-Dimensional Shape

Beijing Key Laboratory of Big Data Technology for Food Safety, School of Computer and Information. National Engineering Laboratory for Agri-product Quality Traceability, Beijing Technology and Business. Pattern Analysis and Machine Intelligence Group, Department of Computer and Information Science, University of Macau, Taipa, Macau 999078, China

Introduction
Related Work
Framework
Feature Extraction
Sketch
A Siamese network hasrecognition been considered to be a special network
Cross-Domain Matching Using Siamese Network
Experiment
Dataset
Evaluation metrics
Evaluation Metrics
Experimental Settings
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call