DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationImage Super-ResolutionSuper-ResolutionUnconditional Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DiffNator: Generating Structured Explanations of Time-Series Differences
In many IoT applications, the central interest lies not in individual sensor signals but in their differences, yet interpreting such differences requires expert knowledge. We propose DiffNator, a framework for structured…
Visual Question AnsweringUIEDP:Underwater Image Enhancement with Diffusion Prior
Underwater image enhancement (UIE) aims to generate clear images from low-quality underwater images. Due to the unavailability of clear reference images, researchers often synthesize them to construct paired datasets for…
Image EnhancementImage GenerationImage Quality AssessmentNo-Reference Image Quality Assessment+1DiffLoss: unleashing diffusion model as constraint for training image restoration network
Image restoration aims to enhance low quality images, producing high quality images that exhibit natural visual characteristics and fine semantic attributes. Recently, the diffusion model has emerged as a powerful techni…
Image GenerationImage RestorationPICD: Versatile Perceptual Image Compression with Diffusion Rendering
Recently, perceptual image compression has achieved significant advancements, delivering high visual quality at low bitrates for natural images. However, for screen content, existing methods often produce noticeable arti…
Image CompressionAmbient Diffusion Omni: Training Good Models with Bad Data
We show how to use low-quality, synthetic, and out-of-distribution images to improve the quality of a diffusion model. Typically, diffusion models are trained on curated datasets that emerge from highly filtered data poo…