Dynamic Bandwidth Allocation for Hybrid Event-RGB Transmission

2025-06-25

AI Summary

To address high data redundancy, excessive bandwidth consumption, and the difficulty of simultaneously achieving real-time deblurring and transmission efficiency in hybrid event-RGB camera systems, this paper proposes a dynamic bandwidth allocation framework for joint event-image (E-I) transmission. Our method explicitly disentangles shared semantic information from modality-specific representations between event streams and RGB frames, leveraging Bayesian modeling and the information bottleneck principle; it then employs a lightweight joint encoder. Furthermore, a scene dynamics-aware mechanism is introduced to adaptively allocate channel resources. Experimental results demonstrate that our approach maintains sub-millisecond deblurring latency while improving PSNR by 2.1 dB and reducing transmission bit rate by 37%, significantly outperforming both unimodal and conventional joint coding methods.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Event cameras asynchronously capture pixel-level intensity changes with extremely low latency. They are increasingly used in conjunction with RGB cameras for a wide range of vision-related applications. However, a major challenge in these hybrid systems lies in the transmission of the large volume of triggered events and RGB images. To address this, we propose a transmission scheme that retains efficient reconstruction performance of both sources while accomplishing real-time deblurring in parallel. Conventional RGB cameras and event cameras typically capture the same scene in different ways, often resulting in significant redundant information across their outputs. To address this, we develop a joint event and image (E-I) transmission framework to eliminate redundancy and thereby optimize channel bandwidth utilization. Our approach employs Bayesian modeling and the information bottleneck method to disentangle the shared and domain-specific information within the E-I inputs. This disentangled information bottleneck framework ensures both the compactness and informativeness of extracted shared and domain-specific information. Moreover, it adaptively allocates transmission bandwidth based on scene dynamics, i.e., more symbols are allocated to events for dynamic details or to images for static information. Simulation results demonstrate that the proposed scheme not only achieves superior reconstruction quality compared to conventional systems but also delivers enhanced deblurring performance.

Problem

• Optimize bandwidth for hybrid event-RGB transmission systems
• Reduce redundancy between event and RGB camera outputs
• Adaptively allocate bandwidth based on scene dynamics

Innovation

• Dynamic bandwidth allocation for hybrid Event-RGB transmission
• Joint event-image framework eliminates redundancy efficiently
• Bayesian modeling optimizes shared and domain-specific information