Image-to-Audio on VGGSound (test)
2.61KL DivergenceIm2Wav
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Im2Wav2026.06 | 2.61 | 7.06 | 19.63 | 7.58 | 41 | |
| Seeing&Hearing2026.06 | 2.69 | 6.15 | 20.96 | 6.87 | 29 | |
| Caption2Audio2026.06 | 2.76 | 7.48 | 32.97 | 5.54 | 21 | |
| AudioX-Basetraining_mode=no specific training with image data2026.06 | 2.81 | 11.47 | 17.03 | 2.68 | 22 | |
| AudioX-Turbotraining_mode=no specific training with image data2026.06 | 2.85 | 11.22 | 16.53 | 2.65 | 23 |