Video-to-Music Generation on Human Evaluation (Scene Cut Videos)
81.54Music Quality Win RateV2M-Zero
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| V2M-ZeroBaseline=SONIQUE2026.03 | 81.54 | 78.46 | |
| V2M-ZeroBaseline Comparison=SONIQUE2026.03 | 81.54 | 78.46 | |
| V2M-ZeroBaseline=VidMuse2026.03 | 74.63 | 59.51 | |
| V2M-ZeroBaseline Comparison=VidMuse2026.03 | 74.63 | 59.51 | |
| V2M-ZeroBaseline=AudioX2026.03 | 73.17 | 61.46 | |
| V2M-ZeroBaseline Comparison=AudioX2026.03 | 73.17 | 61.46 | |
| V2M-ZeroBaseline=Average2026.03 | 71.14 | 66.56 | |
| V2M-ZeroBaseline Comparison=Average2026.03 | 71.14 | 66.56 | |
| V2M-ZeroBaseline=GVMGen2026.03 | 70.29 | 67.39 | |
| V2M-ZeroBaseline Comparison=GVMGen2026.03 | 70.29 | 67.39 | |
| V2M-ZeroBaseline=M2UGen2026.03 | 67.88 | 66.42 | |
| V2M-ZeroBaseline Comparison=M2UGen2026.03 | 67.88 | 66.42 | |
| V2M-ZeroBaseline=MTCV2M2026.03 | 65.35 | 66.14 | |
| V2M-ZeroBaseline Comparison=MTCV2M2026.03 | 65.35 | 66.14 |