公开(公告)号：US20240185386A1

公开(公告)日：2024-06-06

申请号：US18556653

申请日：2021-09-30

申请人： Baidu USA, LLC ,  Baidu.com Times Technology (Beijing) Co., Ltd.

发明人： Zhihong PAN ,  Baopu LI ,  Dongliang HE ,  Wenhao WU ,  Tianwei LIN

IPC分类号： G06T3/4076 ,  G06T3/4046

CPC分类号： G06T3/4076 ,  G06T3/4046

摘要： Image super-resolution (SR) refers to the process of recovering high-resolution (HR) images from low-resolution (LR) inputs. Blind image SR is a more challenging task which involves unknown blurring kernels and characterizes the degradation process from HR to LR. In the present disclosure, embodiments of a variational autoencoder (VAE) are leveraged to train a kernel autoencoder for more accurate degradation representation and more efficient kernel estimation. In one or more embodiments, a kernel-agnostic loss is used to learn more robust kernel features in the latent space from LR inputs without using ground-truth kernel references. In addition, attention-based adaptive pooling is introduced to improve kernel estimation accuracy, and spatially non-uniform kernel features are passed into SR restoration resulting in additional kernel estimation error tolerance. Extensive experiments on synthetic and real-world images show that embodiments of the presented model outperform state-of-the-art methods significantly with the peak signal-to-noise ratio (PSNR) raised considerably.