Natural SciencesComputational EngineeringComputer VisionMachine VisionOptimizationConvex OptimizationDigital Image ProcessingImage EnhancementImage ProcessingImage RestorationReflectance ModelingExecution Time AnalysisImage ThresholdingPartial Differential Equation SolversPartial Differential Equation SystemsSpecular Reflection SuppressionThresholding
Removing undesired reflections from images taken through the glass is of great importance in computer vision. It serves as a means to enhance the image quality for aesthetic purposes as well as to preprocess images in machine learning and pattern recognition applications. We propose a convex model to suppress the reflection from a single input image. Our model implies a partial differential equation with gradient thresholding, which is solved efficiently using Discrete Cosine Transform. Extensive experiments on synthetic and real-world images demonstrate that our approach achieves desirable reflection suppression results and dramatically reduces the execution time.
21
Image smoothing via<i>L</i><sub>0</sub>gradient minimization
Li Xu, Cewu Lu, Yi Xu et al. · 2011 · 886 citations
Arts, Fine Arts, Computer Vision +16
Image smoothing via<i>L</i><sub>0</sub>gradient minimization
Xu Li, Cewu Lu, Yi Xu et al. · ACM Transactions on Graphics · 2011 · 776 citations
Arts, Fine Arts, Computer Vision +16
Single Image Layer Separation Using Relative Smoothness
Yu Li, Michael S. Brown · 2014 · 367 citations
A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing
Qingnan Fan, Jiaolong Yang, Gang Hua et al. · 2017 · 326 citations