Video Quality Evaluation Methodology and Result of AV2 Compression Performance

2026-05-15

AI Summary

This study systematically evaluates the compression efficiency and visual quality of the emerging AV2 video coding standard across diverse application scenarios. To address the limited coverage of existing evaluation frameworks, the work introduces a more realistic test setup incorporating convex-hull-driven adaptive streaming configurations, user-generated content (UGC), and extended chroma subsampling formats. Under common test conditions (CTC) and random access configuration, performance is assessed using BD-rate metrics combined with both PSNR-YUV and VMAF objective quality models. Experimental results demonstrate that AV2 achieves BD-rate savings of 29.81% and 33.79% over AV1 under PSNR-YUV and VMAF, respectively, indicating a substantial improvement in compression performance for next-generation streaming applications.

Abstract

The Alliance for Open Media (AOMedia) has developed the AV2 video coding standard to supersede AV1, aiming for substantial compression efficiency gains across diverse media applications. This paper details the quality and performance evaluation methodology defined in the AV2 Common Test Conditions (CTC), which introduces new evaluation methods and content, including convex-hull-based adaptive streaming (AS) configuration, user-generated content (UGC), and extended chroma formats. We present the coding gains of the AV2 (v13.0) against the AV1 baseline. Experimental results show that AV2 achieves significant Bjøntegaard-Delta Rate (BD-rate) reductions of 29.81\% and 33.79\% for PSNR-YUV and VMAF, respectively, under random access configuration, validating the efficiency of AV2 for next-generation streaming applications.

Problem

• Video Quality Evaluation
• AV2 Compression
• Compression Efficiency
• BD-rate
• Streaming Applications

Innovation

• convex-hull-based adaptive streaming
• user-generated content
• extended chroma formats
• BD-rate reduction
• AV2 compression