Real-Time Frequency Selective Reconstruction through Register-Based Argmax Calculation
Frequency Selective Reconstruction (FSR) is a state-of-the-art algorithm for solving diverse image reconstruction tasks, where a subset of pixel values in the image is missing. However, it entails a high computational complexity due to its iterative, blockwise procedure to reconstruct the missing pixel values. Although the complexity of FSR can be considerably decreased by performing its computations in the frequency domain, the reconstruction procedure still takes multiple seconds up to multiple minutes depending on the parameterization. However, FSR has the potential for a massive parallelization greatly improving its reconstruction time. In this paper, we introduce a novel highly parallelized formulation of FSR adapted to the capabilities of modern GPUs and propose a considerably accelerated calculation of the inherent argmax calculation. Altogether, we achieve a 100-fold speed-up, which enables the usage of FSR for real-time applications.
Code (1)
Tasks
Image ReconstructionSimilar Papers 제목 키워드 기반
Texture-Dependent Frequency Selective Reconstruction of Non-Regularly Sampled Images
There exist many scenarios where pixel information is available only on a non-regular subset of pixel positions. For further processing, however, it is required to reconstruct such images on a regular grid. Besides many …
Jointly Resampling and Reconstructing Corrupted Images for Image Classification using Frequency-Selective Mesh-to-Grid Resampling
Neural networks became the standard technique for image classification throughout the last years. They are extracting image features from a large number of images in a training phase. In a following test phase, the netwo…
Classificationimage-classificationImage ClassificationCentroid adapted frequency selective extrapolation for reconstruction of lost image areas
Lost image areas with different size and arbitrary shape can occur in many scenarios such as error-prone communication, depth-based image rendering or motion compensated wavelet lifting. The goal of image reconstruction …
Image ReconstructionSUPER Decoder Block for Reconstruction-Aware U-Net Variants
Skip-connected encoder-decoder architectures (U-Net variants) are widely adopted for inverse problems but still suffer from information loss, limiting recovery of fine high-frequency details. We present Selectively Suppr…
Crack SegmentationImage DenoisingAdaptive frequency prior for frequency selective reconstruction of images from non-regular subsampling
Image signals typically are defined on a rectangular two-dimensional grid. However, there exist scenarios where this is not fulfilled and where the image information only is available for a non-regular subset of pixel po…