arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1801.09710cs.LGcs.GR
收藏

tempoGAN:一种用于流体流动超分辨率的时间相干体生成对抗网络

tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow

Technical University of Munich(慕尼黑工业大学)

You Xie, Aleksandra Franz, Mengyu Chu, Nils Thuerey

AI总结:

针对流体流动超分辨率问题,提出基于条件GAN的tempoGAN模型,结合时空判别器、物理量输入与物理感知数据增强,实现仅用单步低分辨率数据即可生成高细节、时间相干的四维流体场。

摘要:

我们提出了一种时间相干生成模型,用于解决流体流动的超分辨率问题。本研究是首个采用神经网络合成四维物理场的方法。模型以专为三维体数据推理设计的条件生成对抗网络为基础,除常用的空间判别器外,还采用了新颖的时间判别器,从而生成一致且细节丰富的结果。实验表明,通过引入低分辨率速度或涡量等额外物理量,生成器能够推理出更具真实感的高分辨率细节。这些输入不仅能优化训练过程和生成输出,还提供了艺术控制的途径。我们还采用了物理感知的数据增强步骤,这一环节对避免过拟合和降低内存需求至关重要。通过这种方式,网络能够学习生成具有高度细节化、真实且时间相干特征的平流量。我们的方法仅需单时间步的低分辨率流体数据即可即时运行。我们通过多种复杂输入以及二维和三维场景下的应用,验证了该方法的性能。

英文摘要:

We propose a temporally coherent generative model addressing the super-resolution problem for fluid flows. Our work represents a first approach to synthesize four-dimensional physics fields with neural networks. Based on a conditional generative adversarial network that is designed for the inference of three-dimensional volumetric data, our model generates consistent and detailed results by using a novel temporal discriminator, in addition to the commonly used spatial one. Our experiments show that the generator is able to infer more realistic high-resolution details by using additional physical quantities, such as low-resolution velocities or vorticities. Besides improvements in the training process and in the generated outputs, these inputs offer means for artistic control as well. We additionally employ a physics-aware data augmentation step, which is crucial to avoid overfitting and to reduce memory requirements. In this way, our network learns to generate advected quantities with highly detailed, realistic, and temporally coherent features. Our method works instantaneously, using only a single time-step of low-resolution fluid data. We demonstrate the abilities of our method using a variety of complex inputs and applications in two and three dimensions.

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。

↑