Neural networks have recently been used to analyze diverse physical systems and to identify the underlying dynamics. While existing methods achieve impressive results, they are limited by their strong demand for training data and their weak generalization abilities to out-of-distribution data. To overcome these limitations, in this work we propose to combine neural implicit representations for appearance modeling with neural ordinary differential equations (ODEs) for modelling physical phenomena to obtain a dynamic scene representation that can be identified directly from visual observations. Our proposed model combines several unique advantages: (i) Contrary to existing approaches that require large training datasets, we are able to identify physical parameters from only a single video. (ii) The use of neural implicit representations enables the processing of high-resolution videos and the synthesis of photo-realistic images. (iii) The embedded neural ODE has a known parametric form that allows for the identification of interpretable physical parameters, and (iv) long-term prediction in state space. (v) Furthermore, the photo-realistic rendering of novel scenes with modified physical parameters becomes possible.
翻译:最近,神经网络被用来分析各种物理系统,并查明内在动态。虽然现有方法取得了令人印象深刻的成果,但由于对培训数据的强烈需求及其在传播数据方面一般化能力薄弱,这些方法有限。为了克服这些限制,我们提议在这项工作中,将外观的神经隐含表现与神经普通差异方程式(ODE)相结合,以模拟物理现象,从而获得一种能直接从视觉观测中查明的动态场景表现。我们提议的模型结合了几个独特的优势:(一) 与需要大量培训数据集的现有方法相反,我们只能从单一的视频中确定物理参数。 (二) 使用神经隐含表现使高分辨率视频的处理和光现实图像的合成成为可能。 (三) 嵌入的神经值具有已知的准度形式,可以识别可解释的物理参数,以及(四) 国家空间的长期预测。 (五) 此外,有可能以修改的物理参数对新场景进行摄影现实的描述。