Recent approaches build on implicit neural representations (INRs) to propose generative models over function spaces. However, they are computationally intensive when dealing with inference tasks, such as missing data imputation, or directly cannot tackle them. In this work, we propose a novel deep generative model, named VAMoH. VAMoH combines the capabilities of modeling continuous functions using INRs and the inference capabilities of Variational Autoencoders (VAEs). In addition, VAMoH relies on a normalizing flow to define the prior, and a mixture of hypernetworks to parametrize the data log-likelihood. This gives VAMoH a high expressive capability and interpretability. Through experiments on a diverse range of data types, such as images, voxels, and climate data, we show that VAMoH can effectively learn rich distributions over continuous functions. Furthermore, it can perform inference-related tasks, such as conditional super-resolution generation and in-painting, as well or better than previous approaches, while being less computationally demanding.
翻译:最近的方法建立在隐含神经表征上,以提出功能空间的基因模型;然而,当处理缺失数据估算等推断任务时,这些模型在计算上十分密集,或者直接无法处理。在这项工作中,我们提议了一个新型的深层基因模型,名为VAMoH. VAMoH,它结合了利用 InIRs 和变异自动计算器(VAE)的推断能力来模拟连续功能的能力。此外, VAMoH 依靠一种正常化的流程来定义先前的模型,以及一种将数据日志相似性进行对称的超级网络的混合体。这使得 VAMOH 具有很高的表达能力和可解释性。 通过对图像、氧化物和气候数据等多种数据类型进行实验,我们表明VAMOH 能够有效地了解与连续功能有关的丰富分布。此外,它可以执行与推论有关的任务,例如有条件的超级分辨率生成和绘制,以及比先前的方法更好,同时在计算上要求较少。