# RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionar

arXiv: https://arxiv.org/abs/2308.08721 · HTML: https://mlsanity.com/paper/2308.08721/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 17 Aug 2023.

## Builds on (most cited first, 17 of 17)

- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [Image Super-Resolution by Neural Texture Transfer](https://mlsanity.com/paper/1903.00834/) (2019)
- [Blind Face Restoration via Deep Multi-scale Component Dictionaries](https://mlsanity.com/paper/2008.00418/) (2020)
- [Non-local Attention Optimized Deep Image Compression](https://mlsanity.com/paper/1904.09757/) (2019)
- [Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception](https://mlsanity.com/paper/2002.01155/) (2020)
- [Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression](https://mlsanity.com/paper/2203.10897/) (2022)
- [Learning Content-Weighted Deep Image Compression](https://mlsanity.com/paper/1904.00664/) (2019)
- [Attention-based Multi-Reference Learning for Image Super-Resolution](https://mlsanity.com/paper/2108.13697/) (2021)
- [Extreme Image Coding via Multiscale Autoencoders With Generative Adversarial Optimization](https://mlsanity.com/paper/1904.03851/) (2019)

## Built on by (most cited first, 3 of 3)

- [Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression](https://mlsanity.com/paper/2502.09971/) (2025)
- [Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images](https://mlsanity.com/paper/2505.02949/) (2025)
- [REMAC: Reference-Based Martian Asymmetrical Image Compression](https://mlsanity.com/paper/2601.18547/) (2026)

## Abstract (arXiv)

Thriving underwater applications demand efficient extreme compression technology to realize the transmission of underwater images (UWIs) in very narrow underwater bandwidth. However, existing image compression methods achieve inferior performance on UWIs because they do not consider the characteristics of UWIs: (1) Multifarious underwater styles of color shift and distance-dependent clarity, caused by the unique underwater physical imaging; (2) Massive redundancy between different UWIs, caused by the fact that different UWIs contain several common ocean objects, which have plenty of similarities in structures and semantics. To remove redundancy among UWIs, we first construct an exhaustive underwater multi-scale feature dictionary to provide coarse-to-fine reference features for UWI compression. Subsequently, an extreme UWI compression network with reference to the feature dictionary (RFD-ECNet) is creatively proposed, which utilizes feature match and reference feature variant to significantly remove redundancy among UWIs. To align the multifarious underwater styles and improve the accuracy of feature match, an underwater style normalized block (USNB) is proposed, which utilizes underwater physical priors extracted from the underwater physical imaging model to normalize the underwater styles of dictionary features toward the input. Moreover, a reference feature variant module (RFVM) is designed to adaptively morph the reference features, improving the similarity between the reference and input features. Experimental results on four UWI datasets show that our RFD-ECNet is the first work that achieves a significant BD-rate saving of 31% over the most advanced VVC.