paper-with-me

홈 › Papers

Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models

2025-07-24 · Xingyu Qiu, Mengying Yang, Xinghua Ma, Dong Liang, Fanding Li, Gongning Luo, Wei Wang, Kuanquan Wang, Shuo Li arxiv

Although EDM aims to unify the design space of diffusion models, its reliance on fixed Gaussian noise prevents it from explaining emerging flow-based methods that diffuse arbitrary noise. Moreover, our study reveals that EDM's forcible injection of Gaussian noise has adverse effects on image restoration task, as it corrupts the degraded images, overextends the restoration distance, and increases the task's complexity. To interpret diverse methods for handling distinct noise patterns within a unified theoretical framework and to minimize the restoration distance, we propose EDA, which Elucidates the Design space of Arbitrary-noise diffusion models. Theoretically, EDA expands noise pattern flexibility while preserving EDM's modularity, with rigorous proof that increased noise complexity introduces no additional computational overhead during restoration. EDA is validated on three representative medical image denoising and natural image restoration tasks: MRI bias field correction (global smooth noise), CT metal artifact removal (global sharp noise) and natural image shadow removal (local boundary-aware noise). With only 5 sampling steps, competitive results against specialized methods across medical and natural tasks demonstrate EDA's strong generalization capability for image restoration. Code is available at: https://github.com/PerceptionComputingLab/EDA.

📄 PDF Abstract BibTeX arXiv:2507.18534

Code (0)

등록된 구현이 없습니다.

Tasks

Medical Image DenoisingImage Shadow RemovalImage Restoration

Similar Papers 제목 키워드 기반

Elucidating the Design Space of Diffusion-Based Generative Models

2022-06-01 · Tero Karras, Miika Aittala, Timo Aila, Samuli Laine

We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design c…

Image Generation

Arbitrary-steps Image Super-resolution via Diffusion Inversion

2024-12-12 · CVPR 2025 1 · Zongsheng Yue, Kang Liao, Chen Change Loy

This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We de…

Image Super-ResolutionSuper-Resolution

Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder

2024-03-15 · CVPR 2024 1 · Jinseok Kim, Tae-Kyun Kim

Super-resolution (SR) and image generation are important tasks in computer vision and are widely adopted in real-world applications. Most existing methods, however, generate images only at fixed-scale magnification and s…

DecoderDenoisingDiversityImage Generation+2

Learning to Reconstruct Accelerated MRI Through K-space Cold Diffusion without Noise

2023-11-16 · Guoyao Shen, Mengyu Li, Chad W. Farris, Stephan Anderson 외

Deep learning-based MRI reconstruction models have achieved superior performance these days. Most recently, diffusion models have shown remarkable performance in image generation, in-painting, super-resolution, image edi…

Deep LearningImage GenerationMRI ReconstructionSuper-Resolution

Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization

2025-02-03 · Tao Zhang, Cheng Da, Kun Ding, Huan Yang 외

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preference…

model