用迭代重噪技术提升扩散模型解逆问题的精度与速度
Solving Inverse Problems using Diffusion with Iterative Colored Renoising
- 通过迭代重噪让扩散模型在每步中始终接收白噪声输入
- 在多个线性逆问题上达到当前最优的重建精度和推理速度
- 适合需要高精度图像重建的科研与工业应用
成像逆问题可使用预训练扩散模型以无监督方式求解，但需近似测量条件下的得分函数梯度。我们发现现有方法在反向过程早期的近似效果较差，因此提出一种新方法：在每个扩散步骤中多次重估并重噪估计值。该迭代方法称为快速迭代重噪（FIRE），注入形状适配的彩色噪声，确保预训练扩散模型始终看到白噪声，符合其训练假设。我们将FIRE嵌入DDIM反向过程，得到的DDfire在多个线性逆问题及相位恢复任务上均实现当前最优的准确率与运行效率。代码已开源：https://github.com/matt-bendel/DDfire。
原文摘要 · Abstract (English)
Imaging inverse problems can be solved in an unsupervised manner using pre-trained diffusion models, but doing so requires approximating the gradient of the measurement-conditional score function in the diffusion reverse process. We show that the approximations produced by existing methods are relatively poor, especially early in the reverse process, and so we propose a new approach that iteratively reestimates and "renoises" the estimate several times per diffusion step. This iterative approach, which we call Fast Iterative REnoising (FIRE), injects colored noise that is shaped to ensure that the pre-trained diffusion model always sees white noise, in accordance with how it was trained. We then embed FIRE into the DDIM reverse process and show that the resulting "DDfire" offers state-of-the-art accuracy and runtime on several linear inverse problems, as well as phase retrieval. Our implementation is at https://github.com/matt-bendel/DDfire
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。