受限擴散隱式模型

Constrained Diffusion Implicit Models

November 1, 2024

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

cs.AI

摘要

本文描述了一種使用預訓練擴散模型來解決帶有噪聲的線性反問題的高效算法。在擴散去噪隱式模型（DDIM）範式的基礎上，我們提出了受限擴散隱式模型（CDIM），通過修改擴散更新以對最終輸出施加約束。對於無噪聲的反問題，CDIM確切滿足約束；在有噪聲的情況下，我們將CDIM擴展以滿足對噪聲殘差分佈的確切約束。通過各種任務和指標的實驗顯示了CDIM的強大性能，具有與無約束DDIM相似的推理加速度：比先前的條件擴散方法快10到50倍。我們展示了我們方法在許多問題上的多功能性，包括超分辨率、去噪、修補、去模糊和三維點雲重建。

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.