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 2104.06031cs.CVphysics.flu-dyn
收藏

基于学习自监督的全局输运流体重建方法

Global Transport for Fluid Reconstruction with Learned Self-Supervision

Technical University of Munich(慕尼黑工业大学);ETH Zurich(苏黎世联邦理工学院)

Aleksandra Franz, Barbara Solenthaler, Nils Thuerey

AI总结:

该研究提出一种基于全局输运公式与学习自监督的流体体积流重建方法,结合可微渲染实现端到端重建,仅单视角即可生成高真实感流动,在合成与真实流体数据上均提升了重建效果。

摘要:

我们提出一种通过全局输运公式从稀疏视角重建体积流的新方法。该方法不直接获取观测的时空函数,而是基于单个初始状态重建其运动。此外,我们引入了一种学习型自监督机制,对来自未观测视角的观测结果施加约束。这些视觉约束通过输运约束和可微渲染步骤相结合,形成鲁棒的端到端重建算法。这使得即使仅从单个输入视角也能重建高度真实的流动运动。我们通过多种合成流和真实流验证表明,所提出的输运过程全局重建方法可提升流体运动的重建效果。

英文摘要:

We propose a novel method to reconstruct volumetric flows from sparse views via a global transport formulation. Instead of obtaining the space-time function of the observations, we reconstruct its motion based on a single initial state. In addition we introduce a learned self-supervision that constrains observations from unseen angles. These visual constraints are coupled via the transport constraints and a differentiable rendering step to arrive at a robust end-to-end reconstruction algorithm. This makes the reconstruction of highly realistic flow motions possible, even from only a single input view. We show with a variety of synthetic and real flows that the proposed global reconstruction of the transport process yields an improved reconstruction of the fluid motion.

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。

↑