← Back to all news
arXiv Machine Learning By Fabian Kruse, Lorenzo Baldassari, Ivan Dokmani\'c

Learning Clean Generative Processes from Noisy Measurements

Read the original on arXiv Machine Learning →

The paper investigates learning a generative model for clean images from only noisy observations. It shows that Noise2Noise regression can learn posterior predictions at or above the training noise level, but to predict below that level a consistency constraint is required. The authors derive conditions under which this consistency uniquely determines the continuation to the clean image distribution and validate the approach on CIFAR-10, photon‑counting microscopy, and synthetic aperture radar data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 10

Noise in Diffusion Models Is a Learnable Input

The paper argues that the concrete random noise used in diffusion models is not merely a passive perturbation but a learnable input that can be exploited by the model. By analyzing how clean data and realized noise jointly form the noisy input, the authors show that the model can learn regularities in the data or in the noise structure, and that these two routes can interact. Experiments on MNIST and CIFAR‑10 using pseudorandom streams demonstrate that structured‑noise training can reduce prediction loss, but this advantage disappears when test noise is replaced with IID noise, indicating that the learned dependence is tied to the specific noise structure.

By Shengzhi Deng, Chenqi Ye, Yanze Guo
diffusion
More like this →
arXiv Computer Vision
Aug 25

Pixel-Space Diffusion via Observation Operators

Pixel‑Space Diffusion via Observation Operators introduces a new framework for pixel‑space diffusion models that addresses a scale‑time mismatch in existing methods. By replacing fixed full‑image supervision with a time‑indexed observation trajectory that progresses from coarse structures to the full image, the model aligns supervision with the natural recovery order of image details. The approach employs Gaussian‑Lanczos operators and a GL‑CoDA decoder to refine features progressively, resulting in faster convergence and higher generation quality, achieving an FID of 1.52 on ImageNet‑256.

By Shaojie Guo, Lichen Ma, Haoyang Tong, Yu He, Zipeng Guo, Xiaoan Liu, Feng Yan, Yu Guo, Fei Wang, Junshi Huang, Yan Wang
diffusion
More like this →
arXiv AI
Oct 15

Correction Training for Diffusion Models

arXiv:2610.14136v2 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with no...

By Donghoon Ahn, Runqian Wang, Alexei A. Efros, Taesung Park, Yash Belhe
diffusionsafety
More like this →