# LFIC-DRASC: Deep Light Field Image Compression Using Disentangled Representation and Asymmetrical Strip Convolution

arXiv: https://arxiv.org/abs/2409.11711 · HTML: https://mlsanity.com/paper/2409.11711/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 55 references that are in the map.
- First posted on arXiv 18 Sep 2024.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Density Modeling of Images using a Generalized Normalization Transformation](https://mlsanity.com/paper/1511.06281/) (2015)
- [Strip Pooling: Rethinking Spatial Pooling for Scene Parsing](https://mlsanity.com/paper/2003.13328/) (2020)
- [Disentangling Light Fields for Super-Resolution and Disparity Estimation](https://mlsanity.com/paper/2202.10603/) (2022)
- [Spatial-Angular Interaction for Light Field Image Super-Resolution](https://mlsanity.com/paper/1912.07849/) (2019)
- [Light Field Reconstruction Using Convolutional Network on EPI and Extended Applications](https://mlsanity.com/paper/2103.13043/) (2021)
- [Subjective Quality Database and Objective Study of Compressed Point Clouds With 6DoF Head-Mounted Display](https://mlsanity.com/paper/2008.02501/) (2020)
- [Pseudo Sequence based 2-D hierarchical reference structure for Light-Field Image Compression](https://mlsanity.com/paper/1612.07309/) (2016)
- [SADN: Learned Light Field Image Compression with Spatial-Angular Decorrelation](https://mlsanity.com/paper/2202.10837/) (2022)
- [Light Field Image Coding Using VVC standard and View Synthesis based on Dual Discriminator GAN](https://mlsanity.com/paper/2103.04201/) (2021)
- [Learning-Based Practical Light Field Image Compression Using A Disparity-Aware Model](https://mlsanity.com/paper/2106.11558/) (2021)
- [Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression](https://mlsanity.com/paper/2307.06143/) (2023)

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

- [Fast Implicit Neural Light Field Representation via Geometric Decomposition and Multi-Resolution Low-Rank Features](https://mlsanity.com/paper/2608.13949/) (2026)

## Abstract (arXiv)

Light-Field (LF) image is emerging 4D data of light rays that is capable of realistically presenting spatial and angular information of 3D scene. However, the large data volume of LF images becomes the most challenging issue in real-time processing, transmission, and storage. In this paper, we propose an end-to-end deep LF Image Compression method Using Disentangled Representation and Asymmetrical Strip Convolution (LFIC-DRASC) to improve coding efficiency. Firstly, we formulate the LF image compression problem as learning a disentangled LF representation network and an image encoding-decoding network. Secondly, we propose two novel feature extractors that leverage the structural prior of LF data by integrating features across different dimensions. Meanwhile, disentangled LF representation network is proposed to enhance the LF feature disentangling and decoupling. Thirdly, we propose the LFIC-DRASC for LF image compression, where two Asymmetrical Strip Convolution (ASC) operators, i.e. horizontal and vertical, are proposed to capture long-range correlation in LF feature space. These two ASC operators can be combined with the square convolution to further decouple LF features, which enhances the model ability in representing intricate spatial relationships. Experimental results demonstrate that the proposed LFIC-DRASC achieves an average of 20.5% bit rate reductions comparing with the state-of-the-art methods.