Abstract

High-quality image reconstruction and generating the new image by learning the distribution from the image are very popular in computer vision field. Nevertheless, some promising results have been reported in the literature recently. In this work, we propose a VAE-CapsuleGAN network which can generate high-quality face image with modified rotation angle. We show promising results in our experiment on the CAS-PEAL-R1 face dataset.

Full Text
Paper version not known

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