• Glow: Generative Flowwith Invertible 1×1 Convolutions, Diederik P. Kingma*†, Prafulla Dhariwal∗, NIPS 2018
• Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design, 2019
• https://lilianweng.github.io/lil-log/2018/10/13/flow-based-deep-generative-models.html
• Normalizing Flows: An Introduction and Review of Current Methods, Ivan Kobyzev, Simon J.D. Prince, Marcus A. Brubaker, 2019
• Dinh, L., Krueger, D., and Bengio, Y. (2014). Nice: non-linear independent components estimation. arXiv preprint arXiv:1410.8516.
• Dinh, L., Sohl-Dickstein, J., and Bengio, S. (2016). Density estimation using Real NVP. arXiv preprint arXiv:1605.08803.
• f-VAE
• Neural Spline Flows
• Normalizing Flows for Probabilistic Modeling and Inference
• https://github.com/janosh/awesome-normalizing-flows

https://www.youtube.com/watch?v=u3vVyFVU_lI

GANs and VAEs have demonstrated impressive performance results on challenging tasks such as learning distributions of natural images. However, several issues limit their application in practice. Neither allows for ex-act evaluation of the probability density of new points.

Normalizing Flow is a transformation of a simple probability distribution (e.g., a standard normal) into a more complex distribution by a sequence of invertible and differentiable mappings.

Flow-based generative models, first described in NICE (Dinh et al., 2014) and extended in RealNVP (Dinh et al., 2016). We explain the key ideas behind this class of model in the following sections.