# Real-Time Frequency Selective Reconstruction through Register-Based Argmax Calculation

arXiv: https://arxiv.org/abs/2202.13926 · HTML: https://mlsanity.com/paper/2202.13926/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2022.

## Built on by (most cited first, 1 of 1)

- [Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling](https://mlsanity.com/paper/2209.14431/) (2022)

## Abstract (arXiv)

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.