Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models

• URL: http://arxiv.org/abs/2510.23633v1
• Date: Fri, 24 Oct 2025 07:46:23 GMT
• Title: Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models
• Authors: Xun Su, Hiroyuki Kasai,
• Abstract summary: We propose a novel method that synthesizes an optimal noise vector from a noise subspace to approximate the measurement score.<n>Our method can be applied to a wide range of inverse problem solvers, including image compression.
• Score: 7.219077740523681
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pretrained diffusion models have demonstrated strong capabilities in zero-shot inverse problem solving by incorporating observation information into the generation process of the diffusion models. However, this presents an inherent dilemma: excessive integration can disrupt the generative process, while insufficient integration fails to emphasize the constraints imposed by the inverse problem. To address this, we propose \emph{Noise Combination Sampling}, a novel method that synthesizes an optimal noise vector from a noise subspace to approximate the measurement score, replacing the noise term in the standard Denoising Diffusion Probabilistic Models process. This enables conditional information to be naturally embedded into the generation process without reliance on step-wise hyperparameter tuning. Our method can be applied to a wide range of inverse problem solvers, including image compression, and, particularly when the number of generation steps $T$ is small, achieves superior performance with negligible computational overhead, significantly improving robustness and stability.

Related papers

• SSI-DM: Singularity Skipping Inversion of Diffusion Models [4.736184528345518]
  existing methods produce non-Gaussian noise with poor editability due to the inaccuracy in early noising steps.<n>We propose Singularity Skipping Inversion of Diffusion Models (SSI-DM), which bypasses this singular region by adding small noise before standard inversion.<n>As a plug-and-play technique compatible with general diffusion models, our method achieves superior performance on public image datasets.
  arXiv  Detail & Related papers  (2026-02-02T14:59:58Z)
• Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance [54.88271057438763]
  Noise Awareness Guidance (NAG) is a correction method that explicitly steers sampling trajectories to remain consistent with the pre-defined noise schedule.<n>NAG consistently mitigates noise shift and substantially improves the generation quality of mainstream diffusion models.
  arXiv  Detail & Related papers  (2025-10-14T13:31:34Z)
• Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance [52.705112811734566]
  A novel diffusion-based framework is introduced for solving inverse problems using a piecewise guidance scheme.<n>The proposed method is problem-agnostic and readily adaptable to a variety of inverse problems.<n>The framework achieves a reduction in inference time of (25%) for inpainting with both random and center masks, and (23%) and (24%) for (4times) and (8times) super-resolution tasks.
  arXiv  Detail & Related papers  (2025-07-22T19:35:14Z)
• Noise Conditional Variational Score Distillation [60.38982038894823]
  Noise Conditional Variational Score Distillation (NCVSD) is a novel method for distilling pretrained diffusion models into generative denoisers.<n>By integrating this insight into the Variational Score Distillation framework, we enable scalable learning of generative denoisers.
  arXiv  Detail & Related papers  (2025-06-11T06:01:39Z)
• DAWN-FM: Data-Aware and Noise-Informed Flow Matching for Solving Inverse Problems [4.212663349859165]
  Inverse problems, which involve estimating parameters from incomplete or noisy observations, arise in various fields such as medical imaging.<n>We employ Flow Matching (FM), a generative framework that integrates a deterministic processes to map a simple reference distribution.<n>Our method DAWN-FM: Data-AWare and Noise-informed Flow Matching incorporates data and noise embedding, allowing the model to access representations about the measured data.
  arXiv  Detail & Related papers  (2024-12-06T04:18:49Z)
• NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation [86.7260950382448]
  We propose a novel approach to correct noise for image validity, NoiseDiffusion. NoiseDiffusion performs within the noisy image space and injects raw images into these noisy counterparts to address the challenge of information loss.
  arXiv  Detail & Related papers  (2024-03-13T12:32:25Z)
• Diffusion Posterior Sampling for General Noisy Inverse Problems [50.873313752797124]
  We extend diffusion solvers to handle noisy (non)linear inverse problems via approximation of the posterior sampling. Our method demonstrates that diffusion models can incorporate various measurement noise statistics.
  arXiv  Detail & Related papers  (2022-09-29T11:12:27Z)
• Noise Estimation for Generative Diffusion Models [91.22679787578438]
  In this work, we present a simple and versatile learning scheme that can adjust the noise parameters for any given number of steps. Our approach comes at a negligible computation cost.
  arXiv  Detail & Related papers  (2021-04-06T15:46:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.