arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.04930cs.CVcs.GRcs.LG
收藏

扩散模型的蓝噪声

Blue noise for diffusion models

MPI Informatics(MPI信息学研究所);VIA Center(VIA中心);Google DeepMind(谷歌DeepMind);Google Research(Google研究院);University of Cambridge(剑桥大学)

Xingchang Huang, Corentin Salaün, Cristina Vasconcelos, Christian Theobalt, Cengiz Öztireli, Gurprit Singh

AI总结:

本文提出在确定性扩散模型中引入蓝噪声及相关噪声掩码,考虑图像内和图像间的噪声相关性,以改善训练梯度流并提升生成质量,在多个数据集上以FID指标验证了优于仅用高斯白噪声的方法。

摘要:

现有的大多数扩散模型在所有时间步上使用高斯噪声进行训练和采样,这可能无法最优地考虑去噪网络重建的频率内容。尽管相关噪声在计算机图形学中有多种应用,但其在改进训练过程方面的潜力尚未被充分探索。在本文中,我们引入了一类新颖且通用的扩散模型,该模型考虑了图像内部和图像之间的相关噪声。更具体地说,我们提出了一种时变噪声模型,将相关噪声纳入训练过程,以及一种快速生成相关噪声掩码的方法。我们的模型建立在确定性扩散模型之上,并利用蓝噪声来帮助提高生成质量,相比仅使用高斯白(随机)噪声有所改进。此外,我们的框架允许在单个小批量内引入图像之间的相关性,以改善梯度流。我们使用我们的方法在多种数据集上进行了定性和定量评估,在FID指标上相比现有的确定性扩散模型在不同任务上取得了改进。

英文摘要:

Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed by the denoising network. Despite the diverse applications of correlated noise in computer graphics, its potential for improving the training process has been underexplored. In this paper, we introduce a novel and general class of diffusion models taking correlated noise within and across images into account. More specifically, we propose a time-varying noise model to incorporate correlated noise into the training process, as well as a method for fast generation of correlated noise mask. Our model is built upon deterministic diffusion models and utilizes blue noise to help improve the generation quality compared to using Gaussian white (random) noise only. Further, our framework allows introducing correlation across images within a single mini-batch to improve gradient flow. We perform both qualitative and quantitative evaluations on a variety of datasets using our method, achieving improvements on different tasks over existing deterministic diffusion models in terms of FID metric.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑