Foundation Model-Based Adaptive Semantic Image Transmission for Dynamic Wireless Environments

Foundation model-based semantic transmission has recently shown great potential in wireless image communication. However, existing methods exhibit two major limitations: (i) they fail to account for the varying importance of semantic components across different downstream tasks, and (ii) they do not sufficiently exploit wireless domain knowledge, which leads to limited robustness under dynamic channel conditions. To overcome these challenges, this paper proposes a foundation model-based adaptive semantic image transmission system tailored for dynamic wireless environments, such as autonomous driving. The proposed system decomposes each image into a semantic segmentation map and a compressed representation, enabling task-aware prioritization of critical objects and fine-grained textures. A task-adaptive precoding mechanism then allocates radio resources according to the semantic importance of extracted features. To support accurate precoding, a channel estimation knowledge map (CEKM) is constructed using a conditional diffusion model that integrates user position, velocity, and sparse channel samples to train scenario-specific lightweight estimators. At the receiver, a ControlNet-guided diffusion model reconstructs high-quality images from received semantics, enhancing robustness to channel impairments. Extensive experiments conducted on multiple datasets and channel models, including an unseen 3GPP clustered delay line (CDL) channel model, demonstrate the strong generalization and scalability of the proposed framework. Robust performance is further validated under dynamic channel quality, channel estimation mismatch, and imperfect channel state information (CSI), yielding consistent gains in perceptual quality (e.g., SSIM, LPIPS, FID), task accuracy (IoU), and transmission efficiency. These results highlight the effectiveness of integrating task-aware semantic decomposition, scenario-adaptive channel estimation, and diffusion-based reconstruction for robust semantic transmission under dynamic environments.