# Learning-Based Practical Light Field Image Compression Using A Disparity-Aware Model

arXiv: https://arxiv.org/abs/2106.11558 · HTML: https://mlsanity.com/paper/2106.11558/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 22 Jun 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://mlsanity.com/paper/2007.08739/) (2020)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)
- [Light Field Compression with Disparity Guided Sparse Coding based on Structural Key Views](https://mlsanity.com/paper/1610.03684/) (2016)
- [Light Field Image Coding Using Dual Discriminator Generative Adversarial Network and VVC Temporal Scalability](https://mlsanity.com/paper/2003.12322/) (2020)

## Built on by (most cited first, 2 of 2)

- [LFIC-DRASC: Deep Light Field Image Compression Using Disentangled Representation and Asymmetrical Strip Convolution](https://mlsanity.com/paper/2409.11711/) (2024)
- [View Sub-sampling and Reconstruction for Efficient Light Field Compression](https://mlsanity.com/paper/2208.06464/) (2022)

## Abstract (arXiv)

Light field technology has increasingly attracted the attention of the research community with its many possible applications. The lenslet array in commercial plenoptic cameras helps capture both the spatial and angular information of light rays in a single exposure. While the resulting high dimensionality of light field data enables its superior capabilities, it also impedes its extensive adoption. Hence, there is a compelling need for efficient compression of light field images. Existing solutions are commonly composed of several separate modules, some of which may not have been designed for the specific structure and quality of light field data. This increases the complexity of the codec and results in impractical decoding runtimes. We propose a new learning-based, disparity-aided model for compression of 4D light field images capable of parallel decoding. The model is end-to-end trainable, eliminating the need for hand-tuning separate modules and allowing joint learning of rate and distortion. The disparity-aided approach ensures the structural integrity of the reconstructed light fields. Comparisons with the state of the art show encouraging performance in terms of PSNR and MS-SSIM metrics. Also, there is a notable gain in the encoding and decoding runtimes. Source code is available at https://moha23.github.io/LF-DAAE.