Land-then-transport: A Flow Matching-Based Generative Decoder for Wireless Image Transmission

TL;DR

This paper introduces a low-latency, flow-matching generative decoder for wireless image transmission that integrates physical channel models into a deterministic ODE-based framework, enabling efficient and versatile decoding across various wireless channels.

Contribution

It proposes the land-then-transport paradigm with a channel-aware ODE decoder that reuses trained models for different wireless channels without retraining.

Findings

Achieves consistent gains over JPEG2000+LDPC, DeepJSCC, and diffusion baselines.

Requires only a few ODE steps for good perceptual quality.

Works effectively across AWGN, Rayleigh, and MIMO channels.

Abstract

Due to strict rate and reliability demands, wireless image transmission remains difficult for both classical layered designs and joint source-channel coding (JSCC), especially under low latency. Diffusion-based generative decoders can deliver strong perceptual quality by leveraging learned image priors, but iterative stochastic denoising leads to high decoding delay. To enable low-latency decoding, we propose a flow-matching (FM) generative decoder under a new land-then-transport (LTT) paradigm that tightly integrates the physical wireless channel into a continuous-time probability flow. For AWGN channels, we build a Gaussian smoothing path whose noise schedule indexes effective noise levels, and derive a closed-form teacher velocity field along this path. A neural-network student vector field is trained by conditional flow matching, yielding a deterministic, channel-aware ODE decoder with complexity linear in the number of ODE steps. At inference, it only needs an estimate of the effective noise variance to set the ODE starting time. We further show that Rayleigh fading and MIMO channels can be mapped, via linear MMSE equalization and singular-value-domain processing, to AWGN-equivalent channels with calibrated starting times. Therefore, the same probability path and trained velocity field can be reused for Rayleigh and MIMO without retraining. Experiments on MNIST, Fashion-MNIST, and DIV2K over AWGN, Rayleigh, and MIMO demonstrate consistent gains over JPEG2000+LDPC, DeepJSCC, and diffusion-based baselines, while achieving good perceptual quality with only a few ODE steps. Overall, LTT provides a deterministic, physically interpretable, and computation-efficient framework for generative wireless image decoding across diverse channels.