arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.03026cs.LGcs.CVstat.ML
收藏

Pioneer网络：不断发展的生成式自动编码器

Pioneer Networks: Progressively Growing Generative Autoencoder

Aalto University（阿尔托大学）；GenMind Ltd（GenMind有限公司）

Ari Heljakka, Arno Solin, Juho Kannala

备注：
To appear in ACCV 2018
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

我们引入了一种新的生成式自动编码器网络模型，该模型学习以高质量和高分辨率编码和重建图像，并支持从编码器的潜在空间中进行平滑随机采样。生成对抗网络（GANs）以其模拟随机高质量图像的能力而闻名，但它们无法重建现有图像。以前的工作试图扩展GANs来支持这种推理，但到目前为止，还没有提供令人满意的高质量结果。相反，我们提出了渐进式增长生成自动编码器（PIONEER）网络，它实现了高质量的重建与$128{\times}128$图像，而不需要一个GAN编码器。我们将最近的技术与最近引入的对抗编码器生成器网络相结合，逐步构建网络的各个部分。重建输入图像的能力在许多现实世界的应用中至关重要，并允许对现有图像进行精确的智能操作。我们在图像合成和推理方面取得了可喜的成果，在CelebA推理任务中取得了最先进的成果。

英文摘要：

We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, but they cannot reconstruct existing images. Previous works have attempted to extend GANs to support such inference but, so far, have not delivered satisfactory high-quality results. Instead, we propose the Progressively Growing Generative Autoencoder (PIONEER) network which achieves high-quality reconstruction with $128{\times}128$ images without requiring a GAN discriminator. We merge recent techniques for progressively building up the parts of the network with the recently introduced adversarial encoder-generator network. The ability to reconstruct input images is crucial in many real-world applications, and allows for precise intelligent manipulation of existing images. We show promising results in image synthesis and inference, with state-of-the-art results in CelebA inference tasks.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑