Real-World Light Field Image Super-Resolution via Degradation Modulation
Recent years have witnessed the great advances of deep neural networks (DNNs) in light field (LF) image super-resolution (SR). However, existing DNN-based LF image SR methods are developed on a single fixed degradation (e.g., bicubic downsampling), and thus cannot be applied to super-resolve real LF images with diverse degradation. In this paper, we propose a simple yet effective method for real-world LF image SR. In our method, a practical LF degradation model is developed to formulate the degradation process of real LF images. Then, a convolutional neural network is designed to incorporate the degradation prior into the SR process. By training on LF images using our formulated degradation, our network can learn to modulate different degradation while incorporating both spatial and angular information in LF images. Extensive experiments on both synthetically degraded and real-world LF images demonstrate the effectiveness of our method. Compared with existing state-of-the-art single and LF image SR methods, our method achieves superior SR performance under a wide range of degradation, and generalizes better to real LF images. Codes and models are available at https://yingqianwang.github.io/LF-DMnet/.
Code (3)
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Residual Networks for Light Field Image Super-Resolution
Light field cameras are considered to have many potential applications since angular and spatial information is captured simultaneously. However, the limited spatial resolution has brought lots of difficulties in develop…
Image Super-ResolutionSuper-ResolutionToward Real-World Light Field Super-Resolution
Deep learning has opened up new possibilities for light field super-resolution (SR), but existing methods trained on synthetic datasets with simple degradations (e.g., bicubic downsampling) suffer from poor performance w…
Super-ResolutionOcclusion-aware Unsupervised Learning of Depth from 4-D Light Fields
Depth estimation is a fundamental issue in 4-D light field processing and analysis. Although recent supervised learning-based light field depth estimation methods have significantly improved the accuracy and efficiency o…
Depth EstimationDepth PredictionCutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending
Data augmentation (DA) is an efficient strategy for improving the performance of deep neural networks. Recent DA strategies have demonstrated utility in single image super-resolution (SR). Little research has, howeve…
Data AugmentationDenoisingImage Super-ResolutionSuper-ResolutionIncorporating Degradation Estimation in Light Field Spatial Super-Resolution
Recent advancements in light field super-resolution (SR) have yielded impressive results. In practice, however, many existing methods are limited by assuming fixed degradation models, such as bicubic downsampling, which …
Super-Resolution