论文标题
一般噪声反问题的扩散后取样
Diffusion Posterior Sampling for General Noisy Inverse Problems
论文作者
论文摘要
由于其高质量的重建和将现有迭代求解器结合起来的易于性，因此最近将扩散模型作为强大的生成反问题解决器研究。但是，大多数工作都专注于在无噪声设置中解决简单的线性逆问题，这显着不足以使实际问题的复杂性不足。在这项工作中，我们将扩散求解器扩散求解器，以通过后采样的近似来有效处理一般噪声（非）线性反问题。有趣的是，所得后的采样方案是扩散采样的混合版本，具有歧管约束的梯度，而没有严格的测量一致性投影步骤，与先前的研究相比，在嘈杂的设置中产生了更可取的生成路径。我们的方法表明，扩散模型可以结合各种测量噪声统计数据，例如高斯和泊松，并且还有效地处理了嘈杂的非线性反问题，例如傅立叶相检索和不均匀的脱毛。代码可在https://github.com/dps2022/diffusion-posterior-smpling中找到
Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers. However, most works focus on solving simple linear inverse problems in noiseless settings, which significantly under-represents the complexity of real-world problems. In this work, we extend diffusion solvers to efficiently handle general noisy (non)linear inverse problems via approximation of the posterior sampling. Interestingly, the resulting posterior sampling scheme is a blended version of diffusion sampling with the manifold constrained gradient without a strict measurement consistency projection step, yielding a more desirable generative path in noisy settings compared to the previous studies. Our method demonstrates that diffusion models can incorporate various measurement noise statistics such as Gaussian and Poisson, and also efficiently handle noisy nonlinear inverse problems such as Fourier phase retrieval and non-uniform deblurring. Code available at https://github.com/DPS2022/diffusion-posterior-sampling
