Noise Estimation for Generative Diffusion Models
arXiv:2104.02600
Abstract
Generative diffusion models have emerged as leading models in speech and image generation. However, in order to perform well with a small number of denoising steps, a costly tuning of the set of noise parameters is needed. In this work, we present a simple and versatile learning scheme that can step-by-step adjust those noise parameters, for any given number of steps, while the previous work needs to retune for each number separately. Furthermore, without modifying the weights of the diffusion model, we are able to significantly improve the synthesis results, for a small number of steps. Our approach comes at a negligible computation cost.
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Denoising Diffusion Probabilistic Models
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Generative Modeling by Estimating Gradients of the Data Distribution
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
- Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
- Learning Energy-Based Models by Diffusion Recovery Likelihood
Cited by in corpus (10)
- Diffusion Models in Vision: A Survey
- DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
- Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
- On Fast Sampling of Diffusion Probabilistic Models
- Learning to Efficiently Sample from Diffusion Probabilistic Models
- Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
- Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
- Gotta Go Fast When Generating Data with Score-Based Models
- Score-based Generative Modeling in Latent Space
- Bilateral Denoising Diffusion Models