extit{adder-viz}: Real-Time Visualization Software for Transcoding Event Video

2025-08-20

AI Summary

Existing event video representations face bottlenecks in flexibility, real-time performance, and compression efficiency, hindering their adoption in neuromorphic vision. This paper introduces a real-time visualization framework built upon the unified ADΔER representation, integrating asynchronous pixel-level intensity sampling with a streaming processing architecture to enable low-latency, high-fidelity decoding and visualization of event streams. Implemented openly in Rust under the MIT license, the software significantly enhances transcoding observability and system integrability. It supports cross-platform real-time rendering, efficient lossless/lossy compression, and closed-loop application development, achieving measured throughputs exceeding several million events per second. To our knowledge, this is the first work to deeply embed the ADΔER representation into an end-to-end visualization pipeline, delivering a high-performance, scalable, open-source infrastructure for deploying event cameras in real-time vision tasks.

Technology Category

• Computer Vision: Motion & Tracking
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Time-Series/Data Streams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Data transparency and provenance
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Recent years have brought about a surge in neuromorphic ``event'' video research, primarily targeting computer vision applications. Event video eschews video frames in favor of asynchronous, per-pixel intensity samples. While much work has focused on a handful of representations for specific event cameras, these representations have shown limitations in flexibility, speed, and compressibility. We previously proposed the unified ADΔER representation to address these concerns. This paper introduces numerous improvements to the extit{adder-viz} software for visualizing real-time event transcode processes and applications in-the-loop. The MIT-licensed software is available from a centralized repository at href{https://github.com/ac-freeman/adder-codec-rs}{https://github.com/ac-freeman/adder-codec-rs}.

Problem

• Visualizing real-time transcoding processes for event video
• Addressing limitations in flexibility, speed, and compressibility
• Improving software for event video representation visualization

Innovation

• Real-time visualization software for event video
• Unified ADΔER representation for transcoding
• Asynchronous per-pixel intensity sample processing