ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution

• URL: http://arxiv.org/abs/2303.08714v3
• Date: Fri, 2 Feb 2024 10:36:37 GMT
• Title: ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution
• Abstract summary: ResDiff is a novel Diffusion Probabilistic Model based on Residual structure for Single Image Super-Resolution (SISR) In contrast to the common diffusion-based methods that directly use LR images to guide the noise towards HR space, ResDiff utilizes the CNN's initial prediction to direct the noise towards the residual space between HR space and CNN-predicted space. The experiments on multiple benchmark datasets demonstrate that ResDiff outperforms previous diffusion based methods in terms of shorter model convergence time, superior generation quality, and more diverse samples.
• Score: 4.885537700693487
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adapting the Diffusion Probabilistic Model (DPM) for direct image super-resolution is wasteful, given that a simple Convolutional Neural Network (CNN) can recover the main low-frequency content. Therefore, we present ResDiff, a novel Diffusion Probabilistic Model based on Residual structure for Single Image Super-Resolution (SISR). ResDiff utilizes a combination of a CNN, which restores primary low-frequency components, and a DPM, which predicts the residual between the ground-truth image and the CNN predicted image. In contrast to the common diffusion-based methods that directly use LR images to guide the noise towards HR space, ResDiff utilizes the CNN's initial prediction to direct the noise towards the residual space between HR space and CNN-predicted space, which not only accelerates the generation process but also acquires superior sample quality. Additionally, a frequency-domain-based loss function for CNN is introduced to facilitate its restoration, and a frequency-domain guided diffusion is designed for DPM on behalf of predicting high-frequency details. The extensive experiments on multiple benchmark datasets demonstrate that ResDiff outperforms previous diffusion based methods in terms of shorter model convergence time, superior generation quality, and more diverse samples.

Related papers

• SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion Models [52.40011613324083]
  Joint source-channel coding systems (DeepJSCC) have recently demonstrated remarkable performance in wireless image transmission. Existing methods focus on minimizing distortion between the transmitted image and the reconstructed version at the receiver, often overlooking perceptual quality. We propose SING, a novel framework that formulates the recovery of high-quality images from corrupted reconstructions as an inverse problem.
  arXiv  Detail & Related papers  (2025-03-16T12:32:11Z)
• DeltaDiff: Reality-Driven Diffusion with AnchorResiduals for Faithful SR [10.790771977682763]
  We propose DeltaDiff, a novel frame.work that constrains the difusion process.<n>Our method surpasses state-of-the-art models and generates re-sults with better fidelity.<n>This work establishes a new low-rank constrained par-adigm for applying diffusion models to image reconstruction tasks.
  arXiv  Detail & Related papers  (2025-02-18T06:07:14Z)
• MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers [12.639167101005695]
  Mean Reverting (MR) Diffusion directly modifies the structure of the differential equation (SDE) Current training-free fast samplers are not directly applicable to MR Diffusion. We propose a new algorithm named MaRS (MR Sampler) to reduce the sampling NFEs of MR Diffusion.
  arXiv  Detail & Related papers  (2025-02-11T14:57:33Z)
• Effective Diffusion Transformer Architecture for Image Super-Resolution [63.254644431016345]
  We design an effective diffusion transformer for image super-resolution (DiT-SR) In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks. We analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module.
  arXiv  Detail & Related papers  (2024-09-29T07:14:16Z)
• Timestep-Aware Diffusion Model for Extreme Image Rescaling [47.89362819768323]
  We propose a novel framework called Timestep-Aware Diffusion Model (TADM) for extreme image rescaling. TADM performs rescaling operations in the latent space of a pre-trained autoencoder. It effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-08-17T09:51:42Z)
• Highly Accelerated MRI via Implicit Neural Representation Guided Posterior Sampling of Diffusion Models [2.5412006057370893]
  Implicit neural representation (INR) has emerged as a powerful paradigm for solving inverse problems. Our proposed framework can be a generalizable framework to solve inverse problems in other medical imaging tasks.
  arXiv  Detail & Related papers  (2024-07-03T01:37:56Z)
• Diffusion-Aided Joint Source Channel Coding For High Realism Wireless Image Transmission [24.372996233209854]
  DiffJSCC is a novel framework that produces high-realism images via the conditional diffusion denoising process. It can achieve highly realistic reconstructions for 768x512 pixel Kodak images with only 3072 symbols.
  arXiv  Detail & Related papers  (2024-04-27T00:12:13Z)
• Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Data [56.81246107125692]
  Ambient Diffusion Posterior Sampling (A-DPS) is a generative model pre-trained on one type of corruption. We show that A-DPS can sometimes outperform models trained on clean data for several image restoration tasks in both speed and performance. We extend the Ambient Diffusion framework to train MRI models with access only to Fourier subsampled multi-coil MRI measurements.
  arXiv  Detail & Related papers  (2024-03-13T17:28:20Z)
• Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise [34.65659277870287]
  Research on denoising diffusion models has expanded its application to the field of image restoration. We propose Resfusion, a framework that incorporates the residual term into the diffusion forward process. We show that Resfusion exhibits competitive performance on ISTD dataset, LOL dataset and Raindrop dataset with only five sampling steps.
  arXiv  Detail & Related papers  (2023-11-25T02:09:38Z)
• Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
  Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs. In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
  arXiv  Detail & Related papers  (2023-11-20T08:27:56Z)
• SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models [76.43625653814911]
  Diffusion models have gained popularity for accelerated MRI reconstruction due to their high sample quality. They can effectively serve as rich data priors while incorporating the forward model flexibly at inference time. We introduce SURE-based MRI Reconstruction with Diffusion models (SMRD) to enhance robustness during testing.
  arXiv  Detail & Related papers  (2023-10-03T05:05:35Z)
• CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization [41.64072751889151]
  Low-dose computed tomography (LDCT) images suffer from noise and artifacts due to photon starvation and electronic noise. This paper presents a novel COntextual eRror-modulated gEneralized Diffusion model for low-dose CT (LDCT) denoising, termed CoreDiff.
  arXiv  Detail & Related papers  (2023-04-04T14:13:13Z)
• ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval [68.7008281316644]
  ReDi is a learning-free Retrieval-based Diffusion sampling framework. We show that ReDi improves the model inference efficiency by 2x speedup.
  arXiv  Detail & Related papers  (2023-02-05T03:01:28Z)
• Towards performant and reliable undersampled MR reconstruction via diffusion model sampling [67.73698021297022]
  DiffuseRecon is a novel diffusion model-based MR reconstruction method. It guides the generation process based on the observed signals. It does not require additional training on specific acceleration factors.
  arXiv  Detail & Related papers  (2022-03-08T02:25:38Z)
• iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networks [0.0]
  We present iSeeBetter, a novel GAN-based structural-temporal approach to video super-resolution (VSR) iSeeBetter extracts spatial and temporal information from the current and neighboring frames using the concept of recurrent back-projection networks as its generator. Our results demonstrate that iSeeBetter offers superior VSR fidelity and surpasses state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-06-13T01:36:30Z)

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.