Image Super-Resolution via Iterative Refinement
We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models to conditional image generation and performs super-resolution through a stochastic denoising process. Inference starts with pure Gaussian noise and iteratively refines the noisy output using a U-Net model trained on denoising at various noise levels. SR3 exhibits strong performance on super-resolution tasks at different magnification factors, on faces and natural images. We conduct human evaluation on a standard 8X face super-resolution task on CelebA-HQ, comparing with SOTA GAN methods. SR3 achieves a fool rate close to 50%, suggesting photo-realistic outputs, while GANs do not exceed a fool rate of 34%. We further show the effectiveness of SR3 in cascaded image generation, where generative models are chained with super-resolution models, yielding a competitive FID score of 11.3 on ImageNet.
Code (4)
Tasks
Conditional Image GenerationDenoisingImage GenerationImage Super-ResolutionSuper-ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Iterative Token Evaluation and Refinement for Real-World Super-Resolution
Real-world image super-resolution (RWSR) is a long-standing problem as low-quality (LQ) images often have complex and unidentified degradations. Existing methods such as Generative Adversarial Networks (GANs) or continuo…
Image Super-ResolutionSuper-ResolutionTexture SynthesisACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution
Diffusion models have gained significant popularity in the field of image-to-image translation. Previous efforts applying diffusion models to image super-resolution (SR) have demonstrated that iteratively refining pure G…
DenoisingImage Super-ResolutionImage-to-Image TranslationSuper-ResolutionEnhancing Image Matting in Real-World Scenes with Mask-Guided Iterative Refinement
Real-world image matting is essential for applications in content creation and augmented reality. However, it remains challenging due to the complex nature of scenes and the scarcity of high-quality datasets. To address …
Benchmarkingfeature selectionImage MattingDeep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation
Blind single image super-resolution (SISR) is a challenging task in image processing due to the ill-posed nature of the inverse problem. Complex degradations present in real life images make it difficult to solve this pr…
Image ReconstructionImage Super-ResolutionNoise EstimationSuper-ResolutionRBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network
Modern digital cameras and smartphones mostly rely on image signal processing (ISP) pipelines to produce realistic colored RGB images. However, compared to DSLR cameras, low-quality images are usually obtained in many po…
Image Super-ResolutionSuper-Resolution