8K Codec Low-Latency Livestreaming, and AI Streaming
summary
Shows an implemented pipeline that cuts live-stream latency from tens of seconds to sub-0.5s latency using CMAF/chunked streams, WebRTC for sub‑1s scenarios, and CDN/packaging partners (Akamai, Phoenix) to scale; verifies ~500 ms demos in exhibition. Describes an 8K streaming rollout (Tizen player + content deals in France) and an AI scaler/skillet that downscales before encode and reconstructs on device, claiming better visual quality than traditional super‑resolution and compatibility with existing encoders.
AI-written summary · about
chapters (15)
- 0:00Introduction and latency
- 2:02Low latency streaming tech
- 4:29SHM chunk and WebRTC
- 6:49P2P and server solutions
- 8:28Partnership and demo
- 10:478K content overview
- 11:59Adaptive streaming
- 14:498K content providers
- 17:57Explorers TV partnership
- 23:36Expanding 8K ecosystem
- 25:15API for 8K streaming
- 27:15AI in media processing
- 28:49AI Scaler technology
- 32:36Autoencoder vs SR
- 38:01Experimental results
related talks
10mBuilding an 8k encoder + live streaming platform
19mLow Latency Live from a Different Vantage Point
34mLightning Talks
15mUsing The Power of Edge Compute To Enhance Streaming Delivery
16mImproving Video Delivery and Streaming Performance with...
36mCHUNKY MONKEY
50mDemuxed 2023 Lightning Talks
35mLive Low Latency Video Streaming