Generative Joint Source-Channel Coding for Semantic Image Transmission

• URL: http://arxiv.org/abs/2211.13772v1
• Date: Thu, 24 Nov 2022 19:14:27 GMT
• Title: Generative Joint Source-Channel Coding for Semantic Image Transmission
• Authors: Ecenaz Erdemir, Tze-Yang Tung, Pier Luigi Dragotti, Deniz Gunduz
• Abstract summary: Joint source-channel coding (JSCC) schemes using deep neural networks (DNNs) provide promising results in wireless image transmission. We propose two novel J SCC schemes that leverage the perceptual quality of deep generative models (DGMs) for wireless image transmission.
• Score: 29.738666406095074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent works have shown that joint source-channel coding (JSCC) schemes using deep neural networks (DNNs), called DeepJSCC, provide promising results in wireless image transmission. However, these methods mostly focus on the distortion of the reconstructed signals with respect to the input image, rather than their perception by humans. However, focusing on traditional distortion metrics alone does not necessarily result in high perceptual quality, especially in extreme physical conditions, such as very low bandwidth compression ratio (BCR) and low signal-to-noise ratio (SNR) regimes. In this work, we propose two novel JSCC schemes that leverage the perceptual quality of deep generative models (DGMs) for wireless image transmission, namely InverseJSCC and GenerativeJSCC. While the former is an inverse problem approach to DeepJSCC, the latter is an end-to-end optimized JSCC scheme. In both, we optimize a weighted sum of mean squared error (MSE) and learned perceptual image patch similarity (LPIPS) losses, which capture more semantic similarities than other distortion metrics. InverseJSCC performs denoising on the distorted reconstructions of a DeepJSCC model by solving an inverse optimization problem using style-based generative adversarial network (StyleGAN). Our simulation results show that InverseJSCC significantly improves the state-of-the-art (SotA) DeepJSCC in terms of perceptual quality in edge cases. In GenerativeJSCC, we carry out end-to-end training of an encoder and a StyleGAN-based decoder, and show that GenerativeJSCC significantly outperforms DeepJSCC both in terms of distortion and perceptual quality.

Related papers

• Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
  This study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
  arXiv  Detail & Related papers  (2024-01-25T08:11:27Z)
• The Rate-Distortion-Perception-Classification Tradeoff: Joint Source Coding and Modulation via Inverse-Domain GANs [4.735670734773145]
  We show the existence of a strict tradeoff between channel rate, distortion perception, and classification accuracy. We propose two image compression methods to navigate that tradeoff: theCO algorithm and ID-GAN, which is more general compression. They also demonstrate that the proposed ID-GAN algorithm balances image distortion, perception, classification accuracy, and significantly outperforms traditional separation-based methods.
  arXiv  Detail & Related papers  (2023-12-22T16:06:43Z)
• DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement [77.0360085530701]
  Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments. Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features. Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
  arXiv  Detail & Related papers  (2023-12-12T06:07:21Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• CommIN: Semantic Image Communications as an Inverse Problem with INN-Guided Diffusion Models [20.005671042281246]
  We propose CommIN, which views the recovery of high-quality source images from degraded reconstructions as an inverse problem. We show that our CommIN significantly improves the perceptual quality compared to DeepJSCC under extreme conditions.
  arXiv  Detail & Related papers  (2023-10-02T12:06:58Z)
• Deep Joint Source-Channel Coding with Iterative Source Error Correction [11.41076729592696]
  We propose an iterative source error correction (ISEC) decoding scheme for deep-learning-based joint source-channel code (Deep J SCC) Given a noisyword received through the channel, we use a Deep J SCC encoder and decoder pair to update the code iteratively. The proposed scheme produces more reliable source reconstruction results compared to the baseline when the channel noise characteristics do not match the ones used during training.
  arXiv  Detail & Related papers  (2023-02-17T22:50:58Z)
• Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmission [7.692038874196345]
  In this paper, we introduce adversarial losses to optimize deep J SCC. Our new deep J SCC architecture combines encoder, wireless channel, decoder/generator, and discriminator. 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.
  arXiv  Detail & Related papers  (2022-05-26T03:05:13Z)
• Adaptive Information Bottleneck Guided Joint Source and Channel Coding for Image Transmission [132.72277692192878]
  An adaptive information bottleneck (IB) guided joint source and channel coding (AIB-JSCC) is proposed for image transmission. The goal of AIB-JSCC is to reduce the transmission rate while improving the image reconstruction quality. Experimental results show that AIB-JSCC can significantly reduce the required amount of transmitted data and improve the reconstruction quality.
  arXiv  Detail & Related papers  (2022-03-12T17:44:02Z)
• Asymmetric CNN for image super-resolution [102.96131810686231]
  Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. We propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a mem?ory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution. Our ACNet can effectively address single image super-resolution (SISR), blind SISR and blind SISR of blind noise problems.
  arXiv  Detail & Related papers  (2021-03-25T07:10:46Z)
• Bandwidth-Agile Image Transmission with Deep Joint Source-Channel Coding [7.081604594416339]
  We consider the scenario in which images are transmitted progressively in layers over time or frequency. DeepJSCC-$l$ is an innovative solution that uses convolutional autoencoders. DeepJSCC-$l$ has comparable performance with state of the art digital progressive transmission schemes in the challenging low signal-to-noise ratio (SNR) and small bandwidth regimes.
  arXiv  Detail & Related papers  (2020-09-26T00:11:50Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.