# A GPU-Accelerated Light-field Super-resolution Framework Based on Mixed Noise Model and Weighted Regularization

arXiv: https://arxiv.org/abs/2206.05047 · HTML: https://mlsanity.com/paper/2206.05047/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 44 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 9 of 9)

- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [A System for Acquiring, Processing, and Rendering Panoramic Light Field Stills for Virtual Reality](https://mlsanity.com/paper/1810.08860/) (2018)
- [Light Field Super-Resolution Via Graph-Based Regularization](https://mlsanity.com/paper/1701.02141/) (2017)
- [Variational Disparity Estimation Framework for Plenoptic Image](https://mlsanity.com/paper/1804.06633/) (2018)
- [Bilateral Spectrum Weighted Total Variation for Noisy-Image Super-Resolution and Image Denoising](https://mlsanity.com/paper/2106.00768/) (2021)
- [FL-MISR: Fast Large-Scale Multi-Image Super-Resolution for Computed Tomography Based on Multi-GPU Acceleration](https://mlsanity.com/paper/2108.04315/) (2021)
- [3DVSR: 3D EPI Volume-based Approach for Angular and Spatial Light field Image Super-resolution](https://mlsanity.com/paper/2201.01294/) (2022)

## Abstract (arXiv)

This paper presents a GPU-accelerated computational framework for reconstructing high resolution (HR) LF images under a mixed Gaussian-Impulse noise condition. The main focus is on developing a high-performance approach considering processing speed and reconstruction quality. From a statistical perspective, we derive a joint ℓ1-ℓ2 data fidelity term for penalizing the HR reconstruction error taking into account the mixed noise situation. For regularization, we employ the weighted non-local total variation approach, which allows us to effectively realize LF image prior through a proper weighting scheme. We show that the alternating direction method of multipliers algorithm (ADMM) can be used to simplify the computation complexity and results in a high-performance parallel computation on the GPU Platform. An extensive experiment is conducted on both synthetic 4D LF dataset and natural image dataset to validate the proposed SR model's robustness and evaluate the accelerated optimizer's performance. The experimental results show that our approach achieves better reconstruction quality under severe mixed-noise conditions as compared to the state-of-the-art approaches. In addition, the proposed approach overcomes the limitation of the previous work in handling large-scale SR tasks. While fitting within a single off-the-shelf GPU, the proposed accelerator provides an average speedup of 2.46× and 1.57× for × 2 and × 3 SR tasks, respectively. In addition, a speedup of 77× is achieved as compared to CPU execution.