AI RESEARCH
3DAE: Binaural Quality Assessment for Audio Novel View Synthesis with Spatial Maps and Benchmark
arXiv CS.CV
•
ArXi:2605.30469v1 Announce Type: cross 3D audio and novel-view acoustic synthesis models are usually evaluated with global metrics. However, global metrics often hide where and why binaural prediction fails. We propose a full-reference diagnostic framework that uses time-frequency audio error maps for magnitude, ILD, IPD, temporal alignment, loudness, and high-frequency failures, forming a 3D Audio Error Map (3DAE Map) for visual inspection.