Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction
Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-art performance. Unfortunately, diffusion models have a critical downside - they are inherently slow to sample from, needing few thousand steps of iteration to generate images from pure Gaussian noise. In this work, we show that starting from Gaussian noise is unnecessary. Instead, starting from a single forward diffusion with better initialization significantly reduces the number of sampling steps in the reverse conditional diffusion. This phenomenon is formally explained by the contraction theory of the stochastic difference equations like our conditional diffusion strategy - the alternating applications of reverse diffusion followed by a non-expansive data consistency step. The new sampling strategy, dubbed Come-Closer-Diffuse-Faster (CCDF), also reveals a new insight on how the existing feed-forward neural network approaches for inverse problems can be synergistically combined with the diffusion models. Experimental results with super-resolution, image inpainting, and compressed sensing MRI demonstrate that our method can achieve state-of-the-art reconstruction performance at significantly reduced sampling steps.
Code (0)
등록된 구현이 없습니다.
Tasks
compressed sensingImage InpaintingSuper-ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models
Diffusion models have gained prominence in generating high-quality sequences of text. Nevertheless, current approaches predominantly represent discrete text within a continuous diffusion space, which incurs substantial c…
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
In this paper, we point out that suboptimal noise-data mapping leads to slow training of diffusion models. During diffusion training, current methods diffuse each image across the entire noise space, resulting in a mixtu…
DenoisingFlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models
Optical flow estimation a process of predicting pixel-wise displacement between consecutive frames has commonly been approached as a regression task in the age of deep learning. Despite notable advancements this de f…
DecoderDenoisingOptical Flow EstimationDiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
Recently, diffusion models have emerged as a new paradigm for generative models. Despite the success in domains using continuous signals such as vision and audio, adapting diffusion models to natural language is under-ex…
DiversityText GenerationStochastic Conditional Diffusion Models for Robust Semantic Image Synthesis
Semantic image synthesis (SIS) is a task to generate realistic images corresponding to semantic maps (labels). However, in real-world applications, SIS often encounters noisy user inputs. To address this, we propose Stoc…
Conditional Image GenerationImage GenerationImage-to-Image TranslationNoisy Semantic Image Synthesis