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

📝 Original Info

• Title: Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models
• ArXiv ID: 2510.23633
• Date: 2025-10-24
• Authors: ** 논문에 명시된 저자 정보가 제공되지 않았습니다. (저자 정보가 필요하면 원문을 확인해 주세요.) **

📝 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.

💡 Deep Analysis

📄 Full Content

Reference