Cross-Modal Semantic Successive Refinement for Generative Image Communication over Underwater Acoustic Channels
Abstract
Underwater acoustic communication faces challenges such as limited available bandwidth and complex channel environments, which impose demanding requirements on efficient image transmission and reliable reconstruction. To address these challenges, this paper proposes a generative image communication framework based on cross-modal semantic successive refinement. At the transmitter, text descriptions, compact bottleneck features, and visual side information compressed by residual vector quantization are transmitted. At the receiver, text and bottleneck features are first fused to predict a base estimate of the intermediate visual representation. The received RVQ indices are then used to recover supplementary visual information and perform residual correction, followed by image reconstruction using a one-step Pixel Mean Flow model. During training, a CLIP-based text-image semantic consistency constraint is introduced to preserve the semantic correspondence between generated results and the original text descriptions. During transmission, protection resources are allocated according to the importance of different information branches and RVQ quantization stages. Simulations using COCO 2017 images and measured underwater acoustic channel records from Watermark show that text and bottleneck features provide complementary semantic and structural conditions, RVQ visual side information further improves reconstruction quality, and layered unequal error protection helps improve recovery at low SNRs. Code-rate allocation experiments reveal a tradeoff between the reliability of fundamental conditions and visual-detail reconstruction under a limited visual-feature coding budget, providing guidance for allocating protection resources in underwater acoustic image transmission.
Related
- Goal-Oriented Ordered Autoencoding for Successive Refinement in Progressive Communication
- Successive Refinement Under Strong-Sense Perfect Perception
- Covert Digital Semantic Communication With Movable Antennas: Constellation Shaping, Spatial Optimization, and Semantic Mapping
- Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks
- End-to-End Optical Semantic Communication over a Nonlinear WDM Fiber Link
BibTeX
@misc{pei2026crossmodal,
title = {{Cross-Modal Semantic Successive Refinement for Generative Image Communication over Underwater Acoustic Channels}},
author = {Xu Pei and Bin Wang and Guangxu Zhu and Yi Zhang and Haiyan Fan},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.06205},
eprint = {2611.06205},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.06205},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Cross-Modal Semantic Successive Refinement for Generative Image Communication over Underwater Acoustic Channels
AU - Xu Pei
AU - Bin Wang
AU - Guangxu Zhu
AU - Yi Zhang
AU - Haiyan Fan
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.06205
UR - https://arxiv.org/abs/2611.06205
AB - Underwater acoustic communication faces challenges such as limited available bandwidth and complex channel environments, which impose demanding requirements on efficient image transmission and reliable reconstruction. To address these challenges, this paper proposes a generative image communication framework based on cross-modal semantic successive refinement. At the transmitter, text descriptions, compact bottleneck features, and visual side information compressed by residual vector quantization are transmitted. At the receiver, text and bottleneck features are first fused to predict a base estimate of the intermediate visual representation. The received RVQ indices are then used to recover supplementary visual information and perform residual correction, followed by image reconstruction using a one-step Pixel Mean Flow model. During training, a CLIP-based text-image semantic consistency constraint is introduced to preserve the semantic correspondence between generated results and the original text descriptions. During transmission, protection resources are allocated according to the importance of different information branches and RVQ quantization stages. Simulations using COCO 2017 images and measured underwater acoustic channel records from Watermark show that text and bottleneck features provide complementary semantic and structural conditions, RVQ visual side information further improves reconstruction quality, and layered unequal error protection helps improve recovery at low SNRs. Code-rate allocation experiments reveal a tradeoff between the reliability of fundamental conditions and visual-detail reconstruction under a limited visual-feature coding budget, providing guidance for allocating protection resources in underwater acoustic image transmission.
ER -