Toward Real-world Image Super-resolution via Hardware-based Adaptive Degradation Models
Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e.g., bicubic downsampling. However, these methods only learn the inverse process of the predetermined operation, so they fail to super resolve the real-world LR images; the true formulation deviates from the predetermined operation. To address this problem, we propose a novel supervised method to simulate an unknown degradation process with the inclusion of the prior hardware knowledge of the imaging system. We design an adaptive blurring layer (ABL) in the supervised learning framework to estimate the target LR images. The hyperparameters of the ABL can be adjusted for different imaging hardware. The experiments on the real-world datasets validate that our degradation model can estimate LR images more accurately than the predetermined degradation operation, as well as facilitate existing SR methods to perform reconstructions on real-world LR images more accurately than the conventional approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
BSRA: Block-based Super Resolution Accelerator with Hardware Efficient Pixel Attention
Increasingly, convolution neural network (CNN) based super resolution models have been proposed for better reconstruction results, but their large model size and complicated structure inhibit their real-time hardware imp…
Image ReconstructionSuper-ResolutionReal-World Single Image Super-Resolution Under Rainy Condition
Image super-resolution is an important research area in computer vision that has a wide variety of applications including surveillance, medical imaging etc. Real-world signal image super-resolution has become very popula…
Image Super-ResolutionSuper-ResolutionHigh-Resolution Be Aware! Improving the Self-Supervised Real-World Super-Resolution
Self-supervised learning is crucial for super-resolution because ground-truth images are usually unavailable for real-world settings. Existing methods derive self-supervision from low-resolution images by creating pseudo…
Self-Supervised LearningSuper-ResolutionBenchmarking Super-Resolution Algorithms on Real Data
Over the past decades, various super-resolution (SR) techniques have been developed to enhance the spatial resolution of digital images. Despite the great number of methodical contributions, there is still a lack of comp…
BenchmarkingSuper-ResolutionReal-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network
Deep Convolutional Neural Networks (DCNNs) have exhibited impressive performance on image super-resolution tasks. However, these deep learning-based super-resolution methods perform poorly in real-world super-resolution …
Generative Adversarial NetworkImage Super-ResolutionSuper-ResolutionTransfer Learning