受限扩散隐式模型

Constrained Diffusion Implicit Models

November 1, 2024

作者: Vivek Jayaram, Ira Kemelmacher-Shlizerman, Steven M. Seitz, John Thickstun

cs.AI

摘要

本文描述了一种利用预训练扩散模型解决带噪声线性逆问题的高效算法。在去噪扩散隐式模型（DDIM）范式的基础上，我们提出了受限扩散隐式模型（CDIM），通过修改扩散更新以强制对最终输出施加约束。对于无噪声的逆问题，CDIM 精确满足约束；在有噪声的情况下，我们将 CDIM 推广以满足对噪声残差分布的精确约束。通过在各种任务和指标上进行实验，展示了 CDIM 的强大性能，具有与无约束 DDIM 相似的推理加速度：比先前的条件扩散方法快 10 到 50 倍。我们展示了我们方法的多功能性，涵盖了诸多问题，包括超分辨率、去噪、修补、去模糊和三维点云重建。

English

This paper describes an efficient algorithm for solving noisy linear inverse problems using pretrained diffusion models. Extending the paradigm of denoising diffusion implicit models (DDIM), we propose constrained diffusion implicit models (CDIM) that modify the diffusion updates to enforce a constraint upon the final output. For noiseless inverse problems, CDIM exactly satisfies the constraints; in the noisy case, we generalize CDIM to satisfy an exact constraint on the residual distribution of the noise. Experiments across a variety of tasks and metrics show strong performance of CDIM, with analogous inference acceleration to unconstrained DDIM: 10 to 50 times faster than previous conditional diffusion methods. We demonstrate the versatility of our approach on many problems including super-resolution, denoising, inpainting, deblurring, and 3D point cloud reconstruction.