论文标题

MNIST数据集上的交互式潜在插值

Interactive Latent Interpolation on MNIST Dataset

论文作者

Feizabadi, Mazeyar Moeini, Shujjat, Ali Mohammed, Shahid, Sarah, Hasnain, Zainab

论文摘要

本文将通过基于网络的gan使用降低维度的潜力。在各种实验中,我们显示出合成的视觉上吸引样品,在样品之间有意义地插值,并使用潜在向量进行线性算术。事实证明,甘斯是产生计算机生成图像的一种了不起的技术,与原始图像非常相似。当降低维度作为我们算法的有效应用时,这主要是有用的。我们提出了一种针对甘斯的新体系结构,最终由于后来解释了数学原因而无法工作。然后,我们提出了一个新的基于网络的GAN,该GAN仍利用降低维度降低到浏览器中的速度生成为.2毫秒。最后,我们制作了一个带有线性插值的现代UI来展示作品。借助快速的一代,我们可以生成如此之快,以至于我们可以创建一个动画类型效果,以前从未见过,在Web和移动设备上都可以使用。

This paper will discuss the potential of dimensionality reduction with a web-based use of GANs. Throughout a variety of experiments, we show synthesizing visually-appealing samples, interpolating meaningfully between samples, and performing linear arithmetic with latent vectors. GANs have proved to be a remarkable technique to produce computer-generated images, very similar to an original image. This is primarily useful when coupled with dimensionality reduction as an effective application of our algorithm. We proposed a new architecture for GANs, which ended up not working for mathematical reasons later explained. We then proposed a new web-based GAN that still takes advantage of dimensionality reduction to speed generation in the browser to .2 milliseconds. Lastly, we made a modern UI with linear interpolation to present the work. With the speedy generation, we can generate so fast that we can create an animation type effect that we have never seen before that works on both web and mobile.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源