残余物
扩散过程
计算机科学
降噪
扩散
噪音(视频)
图像复原
过程(计算)
算法
图像(数学)
人工智能
数学优化
图像处理
数学
物理
热力学
知识管理
创新扩散
操作系统
作者
Jiawei Liu,Wei Wang,Huijie Fan,Yinong Wang,Yandong Tang,Liangqiong Qu
出处
期刊:Cornell University - arXiv
日期:2023-01-01
标识
DOI:10.48550/arxiv.2308.13712
摘要
We propose residual denoising diffusion models (RDDM), a novel dual diffusion process that decouples the traditional single denoising diffusion process into residual diffusion and noise diffusion. This dual diffusion framework expands the denoising-based diffusion models, initially uninterpretable for image restoration, into a unified and interpretable model for both image generation and restoration by introducing residuals. Specifically, our residual diffusion represents directional diffusion from the target image to the degraded input image and explicitly guides the reverse generation process for image restoration, while noise diffusion represents random perturbations in the diffusion process. The residual prioritizes certainty, while the noise emphasizes diversity, enabling RDDM to effectively unify tasks with varying certainty or diversity requirements, such as image generation and restoration. We demonstrate that our sampling process is consistent with that of DDPM and DDIM through coefficient transformation, and propose a partially path-independent generation process to better understand the reverse process. Notably, our RDDM enables a generic UNet, trained with only an L1 loss and a batch size of 1, to compete with state-of-the-art image restoration methods. We provide code and pre-trained models to encourage further exploration, application, and development of our innovative framework (https://github.com/nachifur/RDDM).
科研通智能强力驱动
Strongly Powered by AbleSci AI