Source Separation with Deep Generative Priors
This addresses the issue of perceptible artifacts in source separation for richly structured data, offering a method that leverages advanced generative models, though it appears incremental as it builds on existing generative modeling techniques.
The paper tackles the problem of source separation in structured data by introducing a Bayesian approach that uses deep generative models as priors and noise-annealed Langevin dynamics for sampling, achieving state-of-the-art performance on MNIST digit separation with quantitative evaluation on CIFAR-10 and qualitative results on LSUN.
Despite substantial progress in signal source separation, results for richly structured data continue to contain perceptible artifacts. In contrast, recent deep generative models can produce authentic samples in a variety of domains that are indistinguishable from samples of the data distribution. This paper introduces a Bayesian approach to source separation that uses generative models as priors over the components of a mixture of sources, and noise-annealed Langevin dynamics to sample from the posterior distribution of sources given a mixture. This decouples the source separation problem from generative modeling, enabling us to directly use cutting-edge generative models as priors. The method achieves state-of-the-art performance for MNIST digit separation. We introduce new methodology for evaluating separation quality on richer datasets, providing quantitative evaluation of separation results on CIFAR-10. We also provide qualitative results on LSUN.