用一致性训练提升低剂量CT图像质量，单步生成效果更好。
Enhancing Low Dose Computed Tomography Images Using Consistency Training Techniques
- 引入可调噪声分布与正弦课程学习，优化生成轨迹。
- 单步采样下，低剂量CT重建质量超越传统方法。
- 适合医学影像增强场景，尤其关注计算效率的临床应用。
扩散模型在图像修复等生成任务中表现优异，但迭代过程仍计算成本高。一致性模型作为新一类生成模型，可在无需对抗训练的情况下实现高质量数据的单步采样。本文提出β噪声分布，灵活调节噪声水平，并结合正弦课程学习，增强从噪声分布到目标后验分布的轨迹学习，实现高噪声改进的一致性训练（HN-iCT）的监督训练。进一步提出图像条件版本HN-iCT-CN，通过加权注意力门（WAG）以低剂量图像为条件提取关键特征。实验表明，在CIFAR10和CelebA数据集上，使用NFE=1的无条件生成，HN-iCT显著优于基础CT与iCT方法；图像条件模型在低剂量CT扫描增强任务中表现卓越。
原文摘要 · Abstract (English)
Diffusion models have significant impact on wide range of generative tasks, especially on image inpainting and restoration. Although the improvements on aiming for decreasing number of function evaluations (NFE), the iterative results are still computationally expensive. Consistency models are as a new family of generative models, enable single-step sampling of high quality data without the need for adversarial training. In this paper, we introduce the beta noise distribution, which provides flexibility in adjusting noise levels. This is combined with a sinusoidal curriculum that enhances the learning of the trajectory between the noise distribution and the posterior distribution of interest, allowing High Noise Improved Consistency Training (HN-iCT) to be trained in a supervised fashion. Additionally, High Noise Improved Consistency Training with Image Condition (HN-iCT-CN) architecture is introduced, enables to take Low Dose images as a condition for extracting significant features by Weighted Attention Gates (WAG).Our results indicate that unconditional image generation using HN-iCT significantly outperforms basic CT and iCT training techniques with NFE=1 on the CIFAR10 and CelebA datasets. Moreover, our image-conditioned model demonstrates exceptional performance in enhancing low-dose (LD) CT scans.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。