- BiRefNet General
- Open weights · commercially permissiveLicense: MIT
- U²-Net
- Open weights · commercially permissiveLicense: Apache-2.0
BiRefNet General vs u2net
Quantitative comparison: 60 images scored against ground-truth mattes. Lower is better. Use the view controls on each row to switch between transparency, chroma key, and alpha matte on all outputs.
| Metric | BiRefNet General | u2net |
|---|---|---|
| MGE (Edge Quality) | 0.04948 ✓ | 0.07984 |
| MAE (Overall Accuracy) | 0.04262 ✓ | 0.12826 |
- MGE
- 0.04048✓
- MAE
- 0.01865✓
- MGE
- 0.05430
- MAE
- 0.04068
- MGE
- 0.09594✓
- MAE
- 0.06799✓
- MGE
- 0.10749
- MAE
- 0.23142
Photo by Alexander Dummer on Unsplash
- MGE
- 0.02067✓
- MAE
- 0.00625✓
- MGE
- 0.04758
- MAE
- 0.03201
- MGE
- 0.02110
- MAE
- 0.00739✓
- MGE
- 0.01890✓
- MAE
- 0.00949
- MGE
- 0.17845
- MAE
- 0.20501✓
- MGE
- 0.17759✓
- MAE
- 0.42832
Photo by Andreas Rasmussen on Unsplash
- MGE
- 0.03450✓
- MAE
- 0.00754✓
- MGE
- 0.09509
- MAE
- 0.08100
- MGE
- 0.03391✓
- MAE
- 0.02906✓
- MGE
- 0.03862
- MAE
- 0.22676
- MGE
- 0.03369✓
- MAE
- 0.00657✓
- MGE
- 0.06007
- MAE
- 0.03098
- MGE
- 0.01534✓
- MAE
- 0.00932✓
- MGE
- 0.03274
- MAE
- 0.01732
- MGE
- 0.01776✓
- MAE
- 0.00662✓
- MGE
- 0.04736
- MAE
- 0.01496
- MGE
- 0.05518✓
- MAE
- 0.02445✓
- MGE
- 0.06842
- MAE
- 0.04546
- MGE
- 0.08626✓
- MAE
- 0.25936✓
- MGE
- 0.08896
- MAE
- 0.68843
- MGE
- 0.07192✓
- MAE
- 0.15422✓
- MGE
- 0.07888
- MAE
- 0.73180
Photo by Camila Quintero Franco on Unsplash
- MGE
- 0.02070✓
- MAE
- 0.00960✓
- MGE
- 0.03513
- MAE
- 0.03698
- MGE
- 0.06499✓
- MAE
- 0.01274✓
- MGE
- 0.11366
- MAE
- 0.07027
- MGE
- 0.01052✓
- MAE
- 0.00263✓
- MGE
- 0.06189
- MAE
- 0.09543
Photo by Carlo Sierra on Unsplash
- MGE
- 0.01420✓
- MAE
- 0.00333✓
- MGE
- 0.04141
- MAE
- 0.14397
- MGE
- 0.03582✓
- MAE
- 0.01162✓
- MGE
- 0.04762
- MAE
- 0.02104
- MGE
- 0.03407✓
- MAE
- 0.02479✓
- MGE
- 0.05973
- MAE
- 0.10539
Photo by Conor Samuel on Unsplash
- MGE
- 0.06431✓
- MAE
- 0.01097✓
- MGE
- 0.42392
- MAE
- 0.30978
- MGE
- 0.02967✓
- MAE
- 0.00716✓
- MGE
- 0.06526
- MAE
- 0.02066
- MGE
- 0.01780✓
- MAE
- 0.00511✓
- MGE
- 0.02158
- MAE
- 0.00659
- MGE
- 0.02221✓
- MAE
- 0.00778✓
- MGE
- 0.03629
- MAE
- 0.03255
- MGE
- 0.04873✓
- MAE
- 0.01122✓
- MGE
- 0.09893
- MAE
- 0.09053
- MGE
- 0.04918
- MAE
- 0.02346✓
- MGE
- 0.04061✓
- MAE
- 0.02781
- MGE
- 0.01367✓
- MAE
- 0.00401✓
- MGE
- 0.05858
- MAE
- 0.02035
Photo by Lars Bo Nielsen on Unsplash
- MGE
- 0.07271✓
- MAE
- 0.09303✓
- MGE
- 0.09775
- MAE
- 0.11268
Photo by Mayer Tawfik on Unsplash
- MGE
- 0.01818✓
- MAE
- 0.00827✓
- MGE
- 0.03523
- MAE
- 0.02607
- MGE
- 0.01969✓
- MAE
- 0.01374✓
- MGE
- 0.02820
- MAE
- 0.02370
- MGE
- 0.03639✓
- MAE
- 0.01379✓
- MGE
- 0.04968
- MAE
- 0.03139
Photo by Niko Tsviliov on Unsplash
- MGE
- 0.23620✓
- MAE
- 0.14015✓
- MGE
- 0.26436
- MAE
- 0.22743
Photo by Norbert Braun on Unsplash
- MGE
- 0.01254✓
- MAE
- 0.00193✓
- MGE
- 0.05312
- MAE
- 0.08202
- MGE
- 0.05570✓
- MAE
- 0.02558✓
- MGE
- 0.07998
- MAE
- 0.29806
- MGE
- 0.06054
- MAE
- 0.09974✓
- MGE
- 0.05827✓
- MAE
- 0.10070
- MGE
- 0.03188✓
- MAE
- 0.02975✓
- MGE
- 0.04397
- MAE
- 0.05425
- MGE
- 0.01467✓
- MAE
- 0.00332✓
- MGE
- 0.04300
- MAE
- 0.07894
- MGE
- 0.34926✓
- MAE
- 0.46453✓
- MGE
- 0.36861
- MAE
- 0.49657
- MGE
- 0.02090✓
- MAE
- 0.00612✓
- MGE
- 0.06347
- MAE
- 0.03625
- MGE
- 0.00619✓
- MAE
- 0.00277✓
- MGE
- 0.02008
- MAE
- 0.01485
- MGE
- 0.01810✓
- MAE
- 0.00714✓
- MGE
- 0.03800
- MAE
- 0.01532
- MGE
- 0.03517✓
- MAE
- 0.00648✓
- MGE
- 0.06015
- MAE
- 0.14384
- MGE
- 0.02895✓
- MAE
- 0.02783✓
- MGE
- 0.03059
- MAE
- 0.04455
- MGE
- 0.01442✓
- MAE
- 0.00315✓
- MGE
- 0.03554
- MAE
- 0.00845
- MGE
- 0.01079✓
- MAE
- 0.00372✓
- MGE
- 0.02402
- MAE
- 0.00790
- MGE
- 0.01879✓
- MAE
- 0.00851✓
- MGE
- 0.03196
- MAE
- 0.02429
- MGE
- 0.00747✓
- MAE
- 0.00115✓
- MGE
- 0.07269
- MAE
- 0.05231
- MGE
- 0.04204✓
- MAE
- 0.07583
- MGE
- 0.04327
- MAE
- 0.02803✓
- MGE
- 0.09392
- MAE
- 0.06015✓
- MGE
- 0.06458✓
- MAE
- 0.10452
- MGE
- 0.17273✓
- MAE
- 0.03358✓
- MGE
- 0.41585
- MAE
- 0.46956
- MGE
- 0.07979
- MAE
- 0.09417
- MGE
- 0.07450✓
- MAE
- 0.05224✓
- MGE
- 0.09319✓
- MAE
- 0.01831✓
- MGE
- 0.16225
- MAE
- 0.11610
- MGE
- 0.01951✓
- MAE
- 0.00290✓
- MGE
- 0.08913
- MAE
- 0.03994
- MGE
- 0.03390✓
- MAE
- 0.00917✓
- MGE
- 0.10358
- MAE
- 0.04381
- MGE
- 0.01230✓
- MAE
- 0.01388✓
- MGE
- 0.01533
- MAE
- 0.03680
Photo by Vinicius Wiesehofer on Unsplash
- MGE
- 0.04915✓
- MAE
- 0.06760✓
- MGE
- 0.05919
- MAE
- 0.71899
- MGE
- 0.04032✓
- MAE
- 0.21379✓
- MGE
- 0.05586
- MAE
- 0.28043
- MGE
- 0.03049✓
- MAE
- 0.02974
- MGE
- 0.04125
- MAE
- 0.02597✓
- MGE
- 0.03339✓
- MAE
- 0.01185✓
- MGE
- 0.04612
- MAE
- 0.07316
- MGE
- 0.04978✓
- MAE
- 0.01930✓
- MGE
- 0.07274
- MAE
- 0.23800
- MGE
- 0.01854✓
- MAE
- 0.00954✓
- MGE
- 0.02746
- MAE
- 0.02864
Methodology
- Alpha mattes are grayscale masks encoding per-pixel foreground probability. They capture fine edge detail (hair, fur, semi-transparent regions) that binary masks discard.
- Metrics are computed by comparing predicted mattes against a ground-truth reference: MGE measures edge sharpness and MAE measures pixel-level accuracy. Both are lower-is-better.
- Scored images come from Bench v0, where every image has a ground-truth matte. The benchmark page has the full methodology and per-image scores for every model (CSV / JSON).
Photo Credits
Source images are courtesy of the photographers below via Unsplash.