A causal diffusion model reconstructs videos from ultra-low-bitrate semantics and compressed frames using temporal distillation from a bidirectional teacher, outperforming prior baselines.
Generative Semantic Communication: Diffusion Models Beyond Bit Recovery
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Semantic communication is expected to be one of the cores of next-generation AI-based communications. One of the possibilities offered by semantic communication is the capability to regenerate, at the destination side, images or videos semantically equivalent to the transmitted ones, without necessarily recovering the transmitted sequence of bits. The current solutions still lack the ability to build complex scenes from the received partial information. Clearly, there is an unmet need to balance the effectiveness of generation methods and the complexity of the transmitted information, possibly taking into account the goal of communication. In this paper, we aim to bridge this gap by proposing a novel generative diffusion-guided framework for semantic communication that leverages the strong abilities of diffusion models in synthesizing multimedia content while preserving semantic features. We reduce bandwidth usage by sending highly-compressed semantic information only. Then, the diffusion model learns to synthesize semantic-consistent scenes through spatially-adaptive normalizations from such denoised semantic information. We prove, through an in-depth assessment of multiple scenarios, that our method outperforms existing solutions in generating high-quality images with preserved semantic information even in cases where the received content is significantly degraded. More specifically, our results show that objects, locations, and depths are still recognizable even in the presence of extremely noisy conditions of the communication channel. The code is available at https://github.com/ispamm/GESCO.
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
An intention-aware semantic agent system for AI glasses reduces bandwidth by over 50% in simulations while preserving task performance through adaptive preprocessing guided by inferred user intentions.
A multi-user semantic communication framework employs an anchor decoder symmetric to the encoder to mitigate catastrophic forgetting, enabling sequential training and frozen-encoder adaptation for users with distinct decoder architectures.
Q-GESCO uses quantized diffusion models to regenerate images from semantic maps in noisy channels, matching full-precision performance with up to 75% memory and 79% FLOP reductions.
Introduces a null-space diffusion sampling method for training-free multi-user generative semantic communications in OFDMA systems.
The tutorial synthesizes diffusion model techniques for generative semantic communications to achieve high compression while preserving meaning in wireless transmission.
citing papers explorer
-
A Causal Diffusion Model for Video Reconstruction from Ultra-Low-Bitrate Representations
A causal diffusion model reconstructs videos from ultra-low-bitrate semantics and compressed frames using temporal distillation from a bidirectional teacher, outperforming prior baselines.
-
Intention-Aware Semantic Agent Communications for AI Glasses
An intention-aware semantic agent system for AI glasses reduces bandwidth by over 50% in simulations while preserving task performance through adaptive preprocessing guided by inferred user intentions.
-
Anchor-Aided Multi-User Semantic Communication with Adaptive Decoders
A multi-user semantic communication framework employs an anchor decoder symmetric to the encoder to mitigate catastrophic forgetting, enabling sequential training and frozen-encoder adaptation for users with distinct decoder architectures.
-
Lightweight Diffusion Models for Resource-Constrained Semantic Communication
Q-GESCO uses quantized diffusion models to regenerate images from semantic maps in noisy channels, matching full-precision performance with up to 75% memory and 79% FLOP reductions.
-
Training-Free Multi-User Generative Semantic Communications via Null-Space Diffusion Sampling
Introduces a null-space diffusion sampling method for training-free multi-user generative semantic communications in OFDMA systems.
-
Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications
The tutorial synthesizes diffusion model techniques for generative semantic communications to achieve high compression while preserving meaning in wireless transmission.