Diffusion Models With Learned Adaptive Noise

2023-12-20 · Subham Sekhar Sahoo, Aaron Gokaslan, Chris De Sa, Volodymyr Kuleshov

Diffusion models have gained traction as powerful algorithms for synthesizing high-quality images. Central to these algorithms is the diffusion process, a set of equations which maps data to noise in a way that can significantly affect performance. In this paper, we explore whether the diffusion process can be learned from data. Our work is grounded in Bayesian inference and seeks to improve log-likelihood estimation by casting the learned diffusion process as an approximate variational posterior that yields a tighter lower bound (ELBO) on the likelihood. A widely held assumption is that the ELBO is invariant to the noise process: our work dispels this assumption and proposes multivariate learned adaptive noise (MULAN), a learned diffusion process that applies noise at different rates across an image. Specifically, our method relies on a multivariate noise schedule that is a function of the data to ensure that the ELBO is no longer invariant to the choice of the noise schedule as in previous works. Empirically, MULAN sets a new state-of-the-art in density estimation on CIFAR-10 and ImageNet and reduces the number of training steps by 50%. We provide the code, along with a blog post and video tutorial on the project page: https://s-sahoo.com/MuLAN

📄 PDF Abstract BibTeX arXiv:2312.13236

Code (1)

s-sahoo/mulan 공식 구현 jax

Tasks

Bayesian Inference Density Estimation Image Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression

2026-04-08 · Zhenyu Du, Yanbo Gao, Shuai Li, Yiyang Li 외 arxiv

With the great success of diffusion models in image generation, diffusion-based image compression is attracting increasing interests. However, due to the random noise introduced in the diffusion learning, they usually pr…

Image Compression Image Generation

NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training

2026-05-02 · Fang Wu, Haokai Zhao, Da Xing, Hanqun Cao 외 arxiv

Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In this work, we challenge this assumption an…

Bilevel Optimization

Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning

2026-04-18 · Yingzhi Xia, Setthakorn Tanomkiattikun, Liangli Zhen, Zaiwang Gu arxiv

Diffusion models (DMs) have recently shown remarkable performance on inverse problems (IPs). Optimization-based methods can fast solve IPs using DMs as powerful regularizers, but they are susceptible to local minima and …

Non Local Spatial and Angular Matching : Enabling higher spatial resolution diffusion MRI datasets through adaptive denoising

2016-06-23 · Samuel St-Jean, Pierrick Coupé, Maxime Descoteaux

Diffusion magnetic resonance imaging datasets suffer from low Signal-to-Noise Ratio, especially at high b-values. Acquiring data at high b-values contains relevant information and is now of great interest for microstruct…

Denoising Diffusion MRI

Query Lower Bounds for Diffusion Sampling

2026-04-12 · Zhiyang Xun, Eric Price arxiv

Diffusion models generate samples by iteratively querying learned score estimates. A rapidly growing literature focuses on accelerating sampling by minimizing the number of score evaluations, yet the information-theoreti…