IVCVJun 18

DiT-JSCC: Rethinking Deep JSCC with Diffusion Transformers and Semantic Representations

arXiv:2601.0311210.61 citationsh-index: 25Has Code
Predicted impact top 11% in IV · last 90 daysOriginality Highly original
AI Analysis

This work addresses the semantic consistency problem in generative image transmission for wireless communication systems, offering a new backbone that improves performance in extreme low-bandwidth and low-SNR scenarios.

DiT-JSCC introduces a generative joint source-channel coding framework that uses a semantics-detail dual-branch encoder and a diffusion transformer decoder to improve semantic consistency and visual quality in image transmission under extreme channel conditions, outperforming existing JSCC methods.

Generative joint source-channel coding (GJSCC) has emerged as a new Deep JSCC paradigm for achieving high-fidelity and robust image transmission under extreme wireless channel conditions, such as ultra-low bandwidth and low signal-to-noise ratio. Recent studies commonly adopt diffusion models as generative decoders, but they frequently produce visually realistic results with limited semantic consistency. This limitation stems from a fundamental mismatch between reconstruction-oriented JSCC encoders and generative decoders, as the former lack explicit semantic discriminability and fail to provide reliable conditional cues. In this paper, we propose DiT-JSCC, a novel GJSCC backbone that can jointly learn a semantics-prioritized representation encoder and a diffusion transformer (DiT) based generative decoder, our open-source project aims to promote the future research in GJSCC. Specifically, we design a semantics-detail dual-branch encoder that aligns naturally with a coarse-to-fine conditional DiT decoder, prioritizing semantic consistency under extreme channel conditions. Moreover, a training-free adaptive bandwidth allocation strategy inspired by Kolmogorov complexity is introduced to further improve the transmission efficiency, thereby indeed redefining the notion of information value in the era of generative decoding. Extensive experiments demonstrate that DiT-JSCC consistently outperforms existing JSCC methods in both semantic consistency and visual quality, particularly in extreme regimes.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes