Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis

• URL: http://arxiv.org/abs/2207.11192v1
• Date: Sat, 16 Jul 2022 15:00:21 GMT
• Title: Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis
• Authors: Sangyun Lee, Hyungjin Chung, Jaehyeon Kim, Jong Chul Ye
• Abstract summary: diffusion models have shown remarkable results in image synthesis by gradually removing noise and amplifying signals. We propose a novel generative process that synthesizes images in a coarse-to-fine manner. Experiments show that the proposed model outperforms the previous method in FID on LSUN bedroom and church datasets.
• Score: 39.671396431940224
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recently, diffusion models have shown remarkable results in image synthesis by gradually removing noise and amplifying signals. Although the simple generative process surprisingly works well, is this the best way to generate image data? For instance, despite the fact that human perception is more sensitive to the low frequencies of an image, diffusion models themselves do not consider any relative importance of each frequency component. Therefore, to incorporate the inductive bias for image data, we propose a novel generative process that synthesizes images in a coarse-to-fine manner. First, we generalize the standard diffusion models by enabling diffusion in a rotated coordinate system with different velocities for each component of the vector. We further propose a blur diffusion as a special case, where each frequency component of an image is diffused at different speeds. Specifically, the proposed blur diffusion consists of a forward process that blurs an image and adds noise gradually, after which a corresponding reverse process deblurs an image and removes noise progressively. Experiments show that the proposed model outperforms the previous method in FID on LSUN bedroom and church datasets. Code is available at https://github.com/sangyun884/blur-diffusion.

Related papers

• Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment [56.609042046176555]
  suboptimal noise-data mapping leads to slow training of diffusion models. Drawing inspiration from the immiscibility phenomenon in physics, we propose Immiscible Diffusion. Our approach is remarkably simple, requiring only one line of code to restrict the diffuse-able area for each image.
  arXiv  Detail & Related papers  (2024-06-18T06:20:42Z)
• Blind Image Restoration via Fast Diffusion Inversion [17.139433082780037]
  Blind Image Restoration via fast Diffusion (BIRD) is a blind IR method that jointly optimize for the degradation model parameters and the restored image. A key idea in our method is not to modify the reverse sampling, i.e., not to alter all the intermediate latents, once an initial noise is sampled. We experimentally validate BIRD on several image restoration tasks and show that it achieves state of the art performance on all of them.
  arXiv  Detail & Related papers  (2024-05-29T23:38:12Z)
• Boosting Diffusion Models with Moving Average Sampling in Frequency Domain [101.43824674873508]
  Diffusion models rely on the current sample to denoise the next one, possibly resulting in denoising instability. In this paper, we reinterpret the iterative denoising process as model optimization and leverage a moving average mechanism to ensemble all the prior samples. We name the complete approach "Moving Average Sampling in Frequency domain (MASF)"
  arXiv  Detail & Related papers  (2024-03-26T16:57:55Z)
• Improving Denoising Diffusion Models via Simultaneous Estimation of Image and Noise [15.702941058218196]
  This paper introduces two key contributions aimed at improving the speed and quality of images generated through inverse diffusion processes. The first contribution involves re parameterizing the diffusion process in terms of the angle on a quarter-circular arc between the image and noise. The second contribution is to directly estimate both the image ($mathbfx_0$) and noise ($mathbfepsilon$) using our network.
  arXiv  Detail & Related papers  (2023-10-26T05:43:07Z)
• Nested Diffusion Processes for Anytime Image Generation [38.84966342097197]
  We propose an anytime diffusion-based method that can generate viable images when stopped at arbitrary times before completion. In experiments on ImageNet and Stable Diffusion-based text-to-image generation, we show, both qualitatively and quantitatively, that our method's intermediate generation quality greatly exceeds that of the original diffusion model.
  arXiv  Detail & Related papers  (2023-05-30T14:28:43Z)
• DIRE for Diffusion-Generated Image Detection [128.95822613047298]
  We propose a novel representation called DIffusion Reconstruction Error (DIRE) DIRE measures the error between an input image and its reconstruction counterpart by a pre-trained diffusion model. It provides a hint that DIRE can serve as a bridge to distinguish generated and real images.
  arXiv  Detail & Related papers  (2023-03-16T13:15:03Z)
• Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise [52.59444045853966]
  We show that an entire family of generative models can be constructed by varying the choice of image degradation. The success of fully deterministic models calls into question the community's understanding of diffusion models.
  arXiv  Detail & Related papers  (2022-08-19T15:18:39Z)
• Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders [137.1060633388405]
  Diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. We propose a faster and cheaper approach that adds noise not until the data become pure random noise. We show that the proposed model can be cast as an adversarial auto-encoder empowered by both the diffusion process and a learnable implicit prior.
  arXiv  Detail & Related papers  (2022-02-19T20:18:49Z)
• Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction [31.61199061999173]
  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. 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. New sampling strategy, dubbed ComeCloser-DiffuseFaster (CCDF), also reveals a new insight on how the existing feedforward neural network approaches for inverse problems can be synergistically combined with the diffusion models.
  arXiv  Detail & Related papers  (2021-12-09T04:28:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.