Dirk Kutscher

Our paper on "MD2G-Cast: Relay-Coordinated Multicast for Scalable Volumetric Streaming over MoQ" has been accepted for publication at ACM Multimedia 2026..

Abstract

Volumetric streaming for immersive 6DoF experiences remains challenging to scale in multi-user settings. Existing systems treat overlapping field-of-view content as independent per-user flows, leading to redundant data replication across the network. This redundancy saturates shared links and manifests as unstable 𝑃99 tail latency, directly degrading interactive continuity.

We present MD2G-Cast, a relay-coordinated multicast framework over Media over QUIC (MoQ). Our key insight is that relays can act as decision points rather than passive forwarders when volumetric signals, such as viewing overlap, device heterogeneity, and bandwidth dynamics, are incorporated into relay decisions. MD2G-Cast enables relays to form reusable multicast groups and jointly schedule layered delivery, ensuring shared base-layer content is delivered once while enhancement layers are selectively assigned.

We implement MD2G-Cast on top of MoQ and evaluate it on a trace-driven testbed with real-world bandwidth and FoV traces. MD2G-Cast improves average QoE by 19% over multicast baselines while reducing 𝑃99 steady-state delivery delay by up to 30%. Under high concurrency, it achieves 53% higher QoE and up to 58.8% lower 𝑃99 steady-state delivery delay compared to a unicast baseline.

Reference

Ruonan Chai, Yisu Wang, Zili Meng, Dirk Kutscher; MD2G-Cast: Relay-Coordinated Multicast for Scalable Volumetric Streaming over MoQ, accepted for publication at ACM Multimedia 2026; Rio de Janeiro, Brazil — 10–14 November 2026

QUIC is the next transport protocol for the Internet that is currently being standardized by the IETF. My student Thomas Ripping at University of Applied Sciences Emden/Leer has developed cwik, an open, interactive and extensible Clojure framework for automating QUIC interop tests and performance measurements, based on Peter Doornbosch’s Kwik library. It can be used for defining test campaigns programmatically and can enable reproducible experiments and automatic evaluation. The source code is available on github.com.