DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics

• URL: http://arxiv.org/abs/2311.09753v1
• Date: Thu, 16 Nov 2023 10:28:59 GMT
• Title: DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics
• Authors: Aniket Roy, Maiterya Suin, Anshul Shah, Ketul Shah, Jiang Liu, Rama Chellappa
• Abstract summary: We propose a generic "naturalness" preserving loss function, viz., kurtosis concentration (KC) loss. Our motivation stems from the projected kurtosis concentration property of natural images. To retain the "naturalness" of the generated images, we enforce reducing the gap between the highest and lowest kurtosis values.
• Score: 39.457325373431836
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have advanced generative AI significantly in terms of editing and creating naturalistic images. However, efficiently improving generated image quality is still of paramount interest. In this context, we propose a generic "naturalness" preserving loss function, viz., kurtosis concentration (KC) loss, which can be readily applied to any standard diffusion model pipeline to elevate the image quality. Our motivation stems from the projected kurtosis concentration property of natural images, which states that natural images have nearly constant kurtosis values across different band-pass versions of the image. To retain the "naturalness" of the generated images, we enforce reducing the gap between the highest and lowest kurtosis values across the band-pass versions (e.g., Discrete Wavelet Transform (DWT)) of images. Note that our approach does not require any additional guidance like classifier or classifier-free guidance to improve the image quality. We validate the proposed approach for three diverse tasks, viz., (1) personalized few-shot finetuning using text guidance, (2) unconditional image generation, and (3) image super-resolution. Integrating the proposed KC loss has improved the perceptual quality across all these tasks in terms of both FID, MUSIQ score, and user evaluation.

Related papers

• Detecting Generated Images by Fitting Natural Image Distributions [75.31113784234877]
  We propose a novel framework that exploits geometric differences between the data manifold of natural and generated images.<n>We employ a pair of functions engineered to yield consistent outputs for natural images but divergent outputs for generated ones.<n>An image is identified as generated if a transformation along its data manifold induces a significant change in the loss value of a self-supervised model pre-trained on natural images.
  arXiv  Detail & Related papers  (2025-11-03T07:20:38Z)
• Entropy-Driven Genetic Optimization for Deep-Feature-Guided Low-Light Image Enhancement [1.0428401220897083]
  We propose a novel, unsupervised, fuzzy-inspired image enhancement framework guided by NSGA-II algorithm.<n>We use a GPU-accelerated NSGA-II algorithm that balances multiple objectives, namely, increasing image entropy, improving perceptual similarity, and maintaining appropriate brightness.<n>Our model achieves excellent performance with average BRISQUE and NIQE scores of 19.82 and 3.652, respectively, in all unpaired datasets.
  arXiv  Detail & Related papers  (2025-05-16T13:40:56Z)
• FreeEnhance: Tuning-Free Image Enhancement via Content-Consistent Noising-and-Denoising Process [120.91393949012014]
  FreeEnhance is a framework for content-consistent image enhancement using off-the-shelf image diffusion models. In the noising stage, FreeEnhance is devised to add lighter noise to the region with higher frequency to preserve the high-frequent patterns in the original image. In the denoising stage, we present three target properties as constraints to regularize the predicted noise, enhancing images with high acutance and high visual quality.
  arXiv  Detail & Related papers  (2024-09-11T17:58:50Z)
• Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency [51.36674160287799]
  We design a multi-branch deep neural network (DNN) to assess the quality of UHD images from three perspectives. aesthetic features are extracted from low-resolution images downsampled from the UHD ones. Technical distortions are measured using a fragment image composed of mini-patches cropped from UHD images. The salient content of UHD images is detected and cropped to extract quality-aware features from the salient regions.
  arXiv  Detail & Related papers  (2024-09-01T15:26:11Z)
• DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement [77.0360085530701]
  Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments. Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features. Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
  arXiv  Detail & Related papers  (2023-12-12T06:07:21Z)
• ARNIQA: Learning Distortion Manifold for Image Quality Assessment [28.773037051085318]
  No-Reference Image Quality Assessment (NR-IQA) aims to develop methods to measure image quality in alignment with human perception without the need for a high-quality reference image. We propose a self-supervised approach named ARNIQA for modeling the image distortion manifold to obtain quality representations in an intrinsic manner.
  arXiv  Detail & Related papers  (2023-10-20T17:22:25Z)
• Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models [60.63556257324894]
  A key desired property of image generative models is the ability to disentangle different attributes. We propose a simple, light-weight image editing algorithm where the mixing weights of the two text embeddings are optimized for style matching and content preservation. Experiments show that the proposed method can modify a wide range of attributes, with the performance outperforming diffusion-model-based image-editing algorithms.
  arXiv  Detail & Related papers  (2022-12-16T19:58:52Z)
• Perceptual Image Restoration with High-Quality Priori and Degradation Learning [28.93489249639681]
  We show that our model performs well in measuring the similarity between restored and degraded images. Our simultaneous restoration and enhancement framework generalizes well to real-world complicated degradation types.
  arXiv  Detail & Related papers  (2021-03-04T13:19:50Z)
• Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network [92.01145655155374]
  We present an unsupervised image enhancement generative network (UEGAN) It learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner. Results show that the proposed model effectively improves the aesthetic quality of images.
  arXiv  Detail & Related papers  (2020-12-30T03:22:46Z)
• Image Inpainting with Learnable Feature Imputation [8.293345261434943]
  A regular convolution layer applying a filter in the same way over known and unknown areas causes visual artifacts in the inpainted image. We propose (layer-wise) feature imputation of the missing input values to a convolution. We present comparisons on CelebA-HQ and Places2 to current state-of-the-art to validate our model.
  arXiv  Detail & Related papers  (2020-11-02T16:05:32Z)
• Progressively Unfreezing Perceptual GAN [28.330940021951438]
  Generative adversarial networks (GANs) are widely used in image generation tasks, yet the generated images are usually lack of texture details. We propose a general framework, called Progressively Unfreezing Perceptual GAN (PUPGAN), which can generate images with fine texture details.
  arXiv  Detail & Related papers  (2020-06-18T03:12:41Z)

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.