{"ID":2891177,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.17196","arxiv_id":"2507.17196","title":"Hybrid Semantic-Complementary Transmission for High-Fidelity Image Reconstruction","abstract":"Recent advances in semantic communication (SC) have introduced neural network (NN)-based transceivers that convey semantic representation (SR) of signals such as images. However, these NNs are trained over diverse image distributions and thus often fail to reconstruct fine-grained image-specific details. To overcome this limited reconstruction fidelity, we propose an extended SC framework, hybrid semantic communication (HSC), which supplements SR with complementary representation (CR) capturing residual image-specific information. The CR is constructed at the transmitter, and is combined with the actual SC outcome at the receiver to yield a high-fidelity recomposed image. While the transmission load of SR is fixed due to its NN-based structure, the load of CR can be flexibly adjusted to achieve a desirable fidelity. This controllability directly influences the final reconstruction error, for which we derive a closed-form expression and the corresponding optimal CR. Simulation results demonstrate that HSC substantially reduces MSE compared to the baseline SC without CR transmission across various channels and NN architectures.","short_abstract":"Recent advances in semantic communication (SC) have introduced neural network (NN)-based transceivers that convey semantic representation (SR) of signals such as images. However, these NNs are trained over diverse image distributions and thus often fail to reconstruct fine-grained image-specific details. To overcome th...","url_abs":"https://arxiv.org/abs/2507.17196","url_pdf":"https://arxiv.org/pdf/2507.17196v1","authors":"[\"Hyelin Nam\",\"Jihong Park\",\"Jinho Choi\",\"Seong-Lyun Kim\"]","published":"2025-07-23T04:41:11Z","proceeding":"eess.SP","tasks":"[\"eess.SP\"]","methods":"[]","has_code":false}