# Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmission

arXiv: https://arxiv.org/abs/2205.13120 · HTML: https://mlsanity.com/paper/2205.13120/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 15 of 15)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks](https://mlsanity.com/paper/1604.04382/) (2016)
- [Real-Time Adaptive Image Compression](https://mlsanity.com/paper/1705.05823/) (2017)
- [DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedback](https://mlsanity.com/paper/1911.11174/) (2019)
- [Nonlinear Transform Source-Channel Coding for Semantic Communications](https://mlsanity.com/paper/2112.10961/) (2021)
- [Generative Compression](https://mlsanity.com/paper/1703.01467/) (2017)
- [Deep Joint Source-Channel Coding for Wireless Image Transmission](https://mlsanity.com/paper/1809.01733/) (2018)

## Built on by (most cited first, 12 of 12)

- [WITT: A Wireless Image Transmission Transformer for Semantic Communications](https://mlsanity.com/paper/2211.00937/) (2022)
- [Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints](https://mlsanity.com/paper/2407.18468/) (2024)
- [Diffusion-Aided Joint Source Channel Coding For High Realism Wireless Image Transmission](https://mlsanity.com/paper/2404.17736/) (2024)
- [How to Evaluate Semantic Communications for Images with ViTScore Metric?](https://mlsanity.com/paper/2309.04891/) (2023)
- [Rate-Adaptive Generative Semantic Communication Using Conditional Diffusion Models](https://mlsanity.com/paper/2409.02597/) (2024)
- [Deep Image Semantic Communication Model for Artificial Intelligent Internet of Things](https://mlsanity.com/paper/2311.02926/) (2023)
- [Personalized Federated Learning for Generative AI-Assisted Semantic Communications](https://mlsanity.com/paper/2410.02450/) (2024)
- [In-Context Source and Channel Coding](https://mlsanity.com/paper/2601.10267/) (2026)
- [Deep Joint Source-Channel Coding for Efficient and Reliable Cross-Technology Communication](https://mlsanity.com/paper/2402.10072/) (2024)
- [Object-Attribute-Relation Representation Based Video Semantic Communication](https://mlsanity.com/paper/2406.10469/) (2024)
- [Learnable Residual-Based Latent Denoising in Semantic Communication](https://mlsanity.com/paper/2502.07319/) (2025)
- [JSCGC: Joint Source-Channel-Generation Coding for Wireless Generative Communications](https://mlsanity.com/paper/2606.12858/) (2026)

## Abstract (arXiv)

As one novel approach to realize end-to-end wireless image semantic transmission, deep learning-based joint source-channel coding (deep JSCC) method is emerging in both deep learning and communication communities. However, current deep JSCC image transmission systems are typically optimized for traditional distortion metrics such as peak signal-to-noise ratio (PSNR) or multi-scale structural similarity (MS-SSIM). But for low transmission rates, due to the imperfect wireless channel, these distortion metrics lose significance as they favor pixel-wise preservation. To account for human visual perception in semantic communications, it is of great importance to develop new deep JSCC systems optimized beyond traditional PSNR and MS-SSIM metrics. In this paper, we introduce adversarial losses to optimize deep JSCC, which tends to preserve global semantic information and local texture. Our new deep JSCC architecture combines encoder, wireless channel, decoder/generator, and discriminator, which are jointly learned under both perceptual and adversarial losses. Our method yields human visually much more pleasing results than state-of-the-art engineered image coded transmission systems and traditional deep JSCC systems. A user study confirms that achieving the perceptually similar end-to-end image transmission quality, the proposed method can save about 50% wireless channel bandwidth cost.