Diffusion Normalizing Flow
By Qinsheng Zhang, Yongxin Chen. 2021
118 citations recorded by the source corpus.
We present a novel generative modeling method called diffusion normalizing flow based on stochastic differential equations (SDEs). The algorithm consists of two neural SDEs: a forward SDE that gradually adds noise to the data to transform the data into Gaussian random noise, and a backward SDE that gradually removes the noise to sample from the data distribution. By jointly training the two neural SDEs to minimize a common cost function that quantifies the difference between the two, the backward SDE converges to a diffusion process the starts with a Gaussian distribution and ends with the desired data distribution. Our method is closely related to normalizing flow and diffusion probabilistic models and can be viewed as a combination of the two. Compared with normalizing flow, diffusion normalizing flow is able to learn distributions with sharp boundaries. Compared with diffusion probabilistic models, diffusion normalizing flow requires fewer discretization steps and thus has better sampling efficiency. Our algorithm demonstrates competitive performance in both high-dimension data density estimation and image generation tasks.
Subfields: Generative Models
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Generative Models
- Ming-Hsuan Yang
- Tero Karras
- Timo Aila
- Richard Zhang
- Eli Shechtman
- Jun-Yan Zhu
- Daniel Cohen-Or
- Samuli Laine
Citations in the corpus
- Elucidating the Design Space of Diffusion-Based Generative Models (2022, background): “The SDEs of Song et al. [48] can be generalized [20, 55] as a sum of the probability flow ODE of Eq.”
- Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, methodology): “DiffFlow [273] presents a generative modeling algorithm, combining the advantages of flow-based and diffusion models.”
- A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT (2023, unknown): “DiffFlow [133] integrates flow function into”