Spectral Bayesian Uncertainty for Image Super-Resolution
Recently deep learning techniques have significantly advanced image super-resolution (SR). Due to the black-box nature, quantifying reconstruction uncertainty is crucial when employing these deep SR networks. Previous approaches for SR uncertainty estimation mostly focus on capturing pixel-wise uncertainty in the spatial domain. SR uncertainty in the frequency domain which is highly related to image SR is seldom explored. In this paper, we propose to quantify spectral Bayesian uncertainty in image SR. To achieve this, a Dual-Domain Learning (DDL) framework is first proposed. Combined with Bayesian approaches, the DDL model is able to estimate spectral uncertainty accurately, enabling a reliability assessment for high frequencies reasoning from the frequency domain perspective. Extensive experiments under non-ideal premises are conducted and demonstrate the effectiveness of the proposed spectral uncertainty. Furthermore, we propose a novel Spectral Uncertainty based Decoupled Frequency (SUDF) training scheme for perceptual SR. Experimental results show the proposed SUDF can evidently boost perceptual quality of SR results without sacrificing much pixel accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Bayesian Sparse Representation for Hyperspectral Image Super Resolution
Despite the proven efficacy of hyperspectral imaging in many computer vision tasks, its widespread use is hindered by its low spatial resolution, resulting from hardware limitations. We propose a hyperspectral image supe…
Hyperspectral Image Super-ResolutionImage Super-ResolutionSuper-ResolutionSelf-Supervised Uncertainty Estimation For Super-Resolution of Satellite Images
Super-resolution (SR) of satellite imagery is challenging due to the lack of paired low-/high-resolution data. Recent self-supervised SR methods overcome this limitation by exploiting the temporal redundancy in burst obs…
Image Super-ResolutionImage ReconstructionBayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution
In this work, we investigate the value of uncertainty modeling in 3D super-resolution with convolutional neural networks (CNNs). Deep learning has shown success in a plethora of medical image transformation problems, suc…
Bayesian InferenceImage GenerationSuper-ResolutionFast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network
Convolutional neural network (CNN) has achieved unprecedented success in image super-resolution tasks in recent years. However, the network's performance depends on the distribution of the training sets and degrades on o…
Adversarial DefenseImage ReconstructionImage Super-ResolutionSuper-ResolutionBayesian Fusion of Multi-Band Images
In this paper, a Bayesian fusion technique for remotely sensed multi-band images is presented. The observed images are related to the high spectral and high spatial resolution image to be recovered through physical degra…