TokenComSR: Task-Sensitivity-Guided Token Communication for Wireless Image Super-Resolution
Abstract
For resource-constrained wireless edge devices over bandwidth-limited fading channels, wireless image transmission using traditional separate coding suffers from the cliff-effect collapse. Prevailing deep joint source-channel coding (JSCC) based on convolutional neural networks can mitigate this issue but usually fail to preserve patch-level structures, thereby preventing adaptive per-token power allocation and limiting token-domain compensation for super-resolution (SR). To address these challenges, we propose a token communication framework with SR (TokenComSR). Specifically, we conceive a task-sensitive power allocation (TSPA) module and a signal-to-noise ratio (SNR)-conditioned token refinement module (TRM). TSPA distills training estimates of task sensitivity into inference token power weights, while TRM estimates an SNR-conditioned residual to correct channel-induced distortion in the token domain before decoding. Building on TSPA and TRM, the proposed TokenComSR pairs a Swin Transformer-based token transceiver with a receiver-side SR module for resource-constrained wireless image transmission. Simulation results confirm the effectiveness of the proposed TSPA and TRM, demonstrating improvements over separate coding and JSCC-SR baselines in both reconstruction fidelity and perceptual quality.
Related
- Topology-Aware Integrated Sensing, Communication, Charging in Massive Low-Altitude Wireless Network
- Consensus-Aware Co-design of Wireless Multi-Agent Control and Communication Systems
- Cold-Atom Rydberg Array with Spatiotemporal Multiplexing for High-Sensitivity Wireless Communications
- Quantum Annealing for Resource Allocation in Next-Generation Wireless Communication Networks: A QUBO Modeling Guide
- Digital Twin-Guided Wireless Localization via Probabilistic Inverse Learning
BibTeX
@misc{wang2026tokencomsr,
title = {{TokenComSR: Task-Sensitivity-Guided Token Communication for Wireless Image Super-Resolution}},
author = {Ye Wang and Li Qiao and Zhen Gao and Hua Wang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.03735},
eprint = {2609.03735},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.03735},
}
RIS
TY - UNPB
TI - TokenComSR: Task-Sensitivity-Guided Token Communication for Wireless Image Super-Resolution
AU - Ye Wang
AU - Li Qiao
AU - Zhen Gao
AU - Hua Wang
PY - 2026
DA - 2026/09/03
PB - arXiv
DO - 10.48550/arxiv.2609.03735
UR - https://arxiv.org/abs/2609.03735
AB - For resource-constrained wireless edge devices over bandwidth-limited fading channels, wireless image transmission using traditional separate coding suffers from the cliff-effect collapse. Prevailing deep joint source-channel coding (JSCC) based on convolutional neural networks can mitigate this issue but usually fail to preserve patch-level structures, thereby preventing adaptive per-token power allocation and limiting token-domain compensation for super-resolution (SR). To address these challenges, we propose a token communication framework with SR (TokenComSR). Specifically, we conceive a task-sensitive power allocation (TSPA) module and a signal-to-noise ratio (SNR)-conditioned token refinement module (TRM). TSPA distills training estimates of task sensitivity into inference token power weights, while TRM estimates an SNR-conditioned residual to correct channel-induced distortion in the token domain before decoding. Building on TSPA and TRM, the proposed TokenComSR pairs a Swin Transformer-based token transceiver with a receiver-side SR module for resource-constrained wireless image transmission. Simulation results confirm the effectiveness of the proposed TSPA and TRM, demonstrating improvements over separate coding and JSCC-SR baselines in both reconstruction fidelity and perceptual quality.
ER -