The paper introduces SemQAM, a joint semantic-channel coding and modulation framework for generative image transmission that converts source representations directly into modulated QAM symbols. By vector‑quantizing latent features and mapping each index to a QAM symbol, SemQAM allows channel impairments to influence codebook learning and employs conditional expectations of received codewords to mitigate error propagation in autoregressive decoding. Experiments demonstrate that SemQAM-C matches or surpasses conventional source coding methods while reducing channel uses by 18.57% compared to separated schemes, highlighting its efficiency and effectiveness in joint coding.
Digital image transmission typically optimizes source coding, channel coding, and modulation separately, limiting how source representations adapt to channel impairments. We propose SemQAM, a joint se...
arXiv:2606. 12858v1 Announce Type: cross Abstract: Conventional communication systems, including both separation-based coding and learning-based joint source-channel coding (JSCC), are typically designed under Shannon's rate-distortion theory.
arXiv:2610.27374v1 Announce Type: new Abstract: Neural image codecs face a fundamental trade-off between pixel fidelity and perceptual quality. Distortion-optimized codecs preserve pixel-wise fidelit...
Learned image compression (LIC) has achieved impressive rate-distortion performance. However, existing methods remain highly vulnerable to packet loss, a common challenge in satellite and emergency communications.
arXiv:2601. 10267v2 Announce Type: replace Abstract: Separate Source-Channel Coding (SSCC) remains attractive for text transmission due to its modularity and compatibility with mature entropy coders and powerful channel codes.
The paper introduces RAE-CoD, a diffusion-based compression method that operates in a representation autoencoder space to preserve recognizable content even at extremely low bitrates. It addresses the problem of semantic collapse observed in existing codecs when the bitrate approaches zero, showing that reconstruction losses conflict with semantic objectives and that VAE diffusion models lose efficiency in preserving semantics. Experiments on MSCOCO-30K demonstrate that RAE-CoD outperforms competitors, reducing VFM feature MSE and Fréchet Distance ratios by at least 25.7% and 69.1% at 0.001–0.008 bpp while maintaining stable recognizability and quality.
arXiv:2609.39451v1 Announce Type: new Abstract: Progressive autoregressive image codecs provide an appealing paradigm for generative compression by quantizing continuous latents into discrete tokens,...
arXiv:2608.28687v1 Announce Type: new Abstract: Generative models have significantly improved the performance ceiling of image lossy compression at low bitrates by exploiting learned priors. However,...
arXiv:2606. 06273v1 Announce Type: cross Abstract: Lossless pixel-level image transmission is a fundamental regime beyond semantic communications, because exact recovery requires both accurate symbol probability modeling and reliable delivery over noisy channels.
arXiv:2609.03641v2 Announce Type: replace Abstract: Progressive image compression requires a single embedded representation whose received prefixes can be decoded without re-encoding the source. Mode...
Tree-VQ introduces a progressive tree‑structured vector quantization framework for learned image compression, organizing discrete codewords in a hierarchical binary tree where each latent token is represented by a routed root‑to‑leaf path. Every prefix of this path yields a valid quantized representation, enabling coarse reconstructions from shallow nodes and successive refinements from deeper nodes. The method incorporates a prefix‑compatible tree entropy model, rate‑aware refinement scheduling, and hierarchical prefix supervision to achieve efficient, low‑latency compression with superior perceptual quality and fewer parameters compared to existing approaches.
The paper introduces MIRC, an overfitted image codec that quantizes and entropy‑codes all components—including latents, synthesis network, and entropy models—within a single end‑to‑end rate‑distortion framework inspired by NVRC. It adds a multi‑scale representation with cross‑stage parameter sharing to capture cross‑scale redundancy, yielding a 10.5 % BD‑rate saving over VVC on the CLIC2020 professional set. MIRC offers multiple configurations ranging from 1.2 to 2.9 kMAC per pixel, allowing decoding complexity to be tuned to deployment needs.