“A paper called Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks (http://arxiv.org/abs/1604.04382) uses a different approach with similar results and runs about 500 times faster giving 0.25M pixel images at 25Hz. It also seems to result in less randomness from frame to frame https://www.youtube.com/watch?v=PRD8LpPvdHI …”
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
This paper proposes Markovian Generative Adversarial Networks (MGANs), a method for training generative neural networks for efficient texture synthesis. While deep neural network approaches have recently demonstrated remarkable results in terms of synthesis quality, they still come at considerable computational costs (minutes of run-time for low-res images). Our paper addresses this efficiency issue. Instead of a numerical deconvolution in previous work, we precompute a feed-forward, strided convolutional network that captures the feature statistics of Markovian patches and is able to directly generate outputs of arbitrary dimensions. Such network can directly decode brown noise to realistic texture, or photos to artistic paintings. With adversarial training, we obtain quality comparable to recent neural texture synthesis methods. As no optimization is required any longer at generation time, our run-time performance (0.25M pixel images at 25Hz) surpasses previous neural texture synthesizers by a significant margin (at least 500 times faster). We apply this idea to texture synthesis, style transfer, and video stylization.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及- Real-Time Texture Synthesis with Markovian Generative Adversarial Networks ↗fitzwatermellow · 2016-04-18 · 66 分