Constrained Diffusion Implicit Models
This provides an efficient solution for tasks like super-resolution and denoising, though it is incremental as it builds on existing diffusion models.
The paper tackles noisy linear inverse problems by proposing constrained diffusion implicit models (CDIM), which modify diffusion updates to enforce constraints on outputs, resulting in strong performance and 10 to 50 times faster inference than previous conditional diffusion methods.
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.