Face Super-Resolution Using Stochastic Differential Equations

Abstract

Diffusion models have proven effective for various applications such as images, audio and graph generation. Other important applications are image super-resolution and the solution of inverse problems. More recently, some works have used stochastic differential equations (SDEs) to generalize diffusion models to continuous time. In this work, we introduce SDEs to generate super-resolution face images. To the best of our knowledge, this is the first time SDEs have been used for such an application. The proposed method provides an improved peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and consistency than the existing super-resolution methods based on diffusion models. In particular, we also assess the potential application of this method for the face recognition task. A generic facial feature extractor is used to compare the super-resolution images with the ground truth and superior results were obtained compared with other methods. Our code is publicly available at https://github.com/marcelowds/sr-sde

Accepted for presentation at the Conference on Graphics, Patterns and Images (SIBGRAPI) 2022

References in corpus (3)

• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
• Learning Spatial Attention for Face Super-Resolution
• A First Look at Dataset Bias in License Plate Recognition

Cited by in corpus (4)

• Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layers
• Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution
• Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach
• Robust Face Super-Resolution and Recognition Through Multi-Feature Aggregation in Diffusion Models