Abstract
In order to improve the accuracy of 3D reconstruction from single image, a deep learning based neural network is proposed by improving the Pix2Vox network for 3D reconstruction from single image. Firstly, multi-scale connection and channel attention mechanism are added to the Pix2Vox network structure to retain multi-scale information and enhance key feature learning. Secondly, a threshold calculation module is proposed to implement the threshold setting method adapted to different categories and optimize the threshold value. Finally, a fusion loss function is proposed to fuse the structural loss and the class loss of the model to reduce the influence of unbalanced data and class differences on the reconstruction effect. The experimental results show that the average IoU of the proposed network is 0.670 in the 13 model categories of ShapeNet dataset, indicating that better 3D reconstruction performance can be achieved than using the Pix2Vox and other networks.
Sign-in/Register to access full text options 
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 callMore From: Journal of Computer-Aided Design & Computer Graphics
Disclaimer: 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.
