- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The authors introduce V2SA-Bench, a source-aware benchmark for video-to-spatial audio models, built on a human-annotated dataset of 1,274 videos across perspective and 360° videos, focusing on stereo and binaural audio and extending to first-order ambisonics.
Critical strengths
- The figures are clear.
- The paper is well organized.
- The benchmark is import and the problem is indeed important.
Critical weaknesses
-
The writing needs further improvement. For example, Lines 110 and 112 convey nearly identical information about the dataset and benchmark. Since the paper does not involve training, I find this distinction unnecessary.
-
The paper lacks a comparison table with existing benchmarks in terms of scale, characteristics, and evaluation capabilities. I believe such a comparison is essential for a benchmark-focused paper.
-
I find the reported insight that “current models are strongly center-biased with spatial alignment as the key bottleneck” rather unsurprising. This seems to be a well-known limitation rather than a novel finding.
-
I am confused by the “high qual” and “low qual” labels in Figure 2. Their meanings and distinctions should be better explained.
-
The paper repeatedly mentions Qwen3-Omni without specifying the exact model variant or size. This information is essential for reproducibility.
-
The paper lacks a user study examining the alignment between V2SA-Bench and human preferences. Reporting correlation coefficients between benchmark scores and human judgments would be important for validating the reliability of the proposed benchmark.
Questions for authors
See above.