Abstract
3D data can be instrumental to the computer vision field as it provides insightful information about the full 3D models' geometry. Recently, with easy access to both computational power and huge 3D databases, it is feasible to apply convolutional neural networks to automatically extract the 3D models' features. This paper presents a novel approach, called 2DSlicesNet, which deals with the issue of 3D model retrieval and classification using a 2D slice-based representation with a 3D convolutional neural network. The assumption in this context is that similar 3D models will be composed of almost identical 2D slices. Therefore, we first transform each normalized 3D model into a set of 2D slices corresponding to its first main axis, and then use them as input data to our 3D convolutional neural network. Experimental results and comparison with state-of-the-art approaches, using ModelNet10 and ModelNet40 datasets, prove that our proposed 2DSlicesNet approach can reach notable rates of accuracy in classification and retrieval.
Highlights
With the rapid advancement of 3D object capturing instruments and computing power, there is a growing number of 3D models in different areas [1], such as medical simulation, computer vision, computer graphics, computer-aided design and architectural design
The findings of our experiments demonstrate that our proposed approach can generate comparable results, on both 3D model retrieval and classification tasks, in comparison with the state-of-the-art methods, which show the efficiency of the 2DSlicesNet
CONVOLUTIONAL NEURAL NETWORKS To begin with, we review a few key features of convolutional neural network (CNN) which were presented by LeCun et al [36]
Summary
With the rapid advancement of 3D object capturing instruments and computing power, there is a growing number of 3D models in different areas [1], such as medical simulation, computer vision, computer graphics, computer-aided design and architectural design. The authors proposed LonchaNet, a 3D model classification approach based on 2D slices They extracted three 2D slices for each 3D model corresponding to XY, XZ, and YZ planes. Taybi et al.: 2DSlicesNet: A 2D Slice-Based CNN for 3D Object Retrieval and Classification To address all these limitations, a novel approach called 2DSlicesNet is posited, which combines successive 2D slices for 3D characteristic learning by using 3D convolutional neural network (3DCNN). The findings of our experiments demonstrate that our proposed approach can generate comparable results, on both 3D model retrieval and classification tasks, in comparison with the state-of-the-art methods, which show the efficiency of the 2DSlicesNet. The remainder of the paper is organized as follows.
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
