- U²-Net
- Open weights · commercially permissiveLicense: Apache-2.0
- U²-NetP
- Open weights · commercially permissiveLicense: Apache-2.0
u2net vs u2netp
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 | u2net | u2netp |
|---|---|---|
| MGE (Edge Quality) | 0.07984 ✓ | 0.08033 |
| MAE (Overall Accuracy) | 0.12826 ✓ | 0.14045 |
- MGE
- 0.05430
- MAE
- 0.04068✓
- MGE
- 0.05374✓
- MAE
- 0.04748
- MGE
- 0.10749✓
- MAE
- 0.23142
- MGE
- 0.11020
- MAE
- 0.08004✓
Photo by Alexander Dummer on Unsplash
- MGE
- 0.04758✓
- MAE
- 0.03201✓
- MGE
- 0.05297
- MAE
- 0.07285
- MGE
- 0.01890
- MAE
- 0.00949
- MGE
- 0.01771✓
- MAE
- 0.00816✓
- MGE
- 0.17759✓
- MAE
- 0.42832✓
- MGE
- 0.18184
- MAE
- 0.49191
Photo by Andreas Rasmussen on Unsplash
- MGE
- 0.09509✓
- MAE
- 0.08100✓
- MGE
- 0.09894
- MAE
- 0.10206
- MGE
- 0.03862✓
- MAE
- 0.22676
- MGE
- 0.03897
- MAE
- 0.22444✓
- MGE
- 0.06007
- MAE
- 0.03098✓
- MGE
- 0.05958✓
- MAE
- 0.06814
- MGE
- 0.03274
- MAE
- 0.01732✓
- MGE
- 0.02975✓
- MAE
- 0.01762
- MGE
- 0.04736✓
- MAE
- 0.01496✓
- MGE
- 0.05210
- MAE
- 0.05059
- MGE
- 0.06842
- MAE
- 0.04546
- MGE
- 0.06157✓
- MAE
- 0.03072✓
- MGE
- 0.08896✓
- MAE
- 0.68843
- MGE
- 0.09131
- MAE
- 0.68586✓
- MGE
- 0.07888
- MAE
- 0.73180✓
- MGE
- 0.07758✓
- MAE
- 0.73785
Photo by Camila Quintero Franco on Unsplash
- MGE
- 0.03513
- MAE
- 0.03698
- MGE
- 0.02327✓
- MAE
- 0.01315✓
- MGE
- 0.11366✓
- MAE
- 0.07027
- MGE
- 0.11602
- MAE
- 0.06524✓
- MGE
- 0.06189✓
- MAE
- 0.09543
- MGE
- 0.06224
- MAE
- 0.04251✓
Photo by Carlo Sierra on Unsplash
- MGE
- 0.04141✓
- MAE
- 0.14397✓
- MGE
- 0.04206
- MAE
- 0.23785
- MGE
- 0.04762✓
- MAE
- 0.02104✓
- MGE
- 0.05232
- MAE
- 0.02940
- MGE
- 0.05973
- MAE
- 0.10539
- MGE
- 0.05778✓
- MAE
- 0.06437✓
Photo by Conor Samuel on Unsplash
- MGE
- 0.42392
- MAE
- 0.30978✓
- MGE
- 0.41291✓
- MAE
- 0.35612
- MGE
- 0.06526✓
- MAE
- 0.02066✓
- MGE
- 0.06844
- MAE
- 0.02526
- MGE
- 0.02158✓
- MAE
- 0.00659✓
- MGE
- 0.02605
- MAE
- 0.00943
- MGE
- 0.03629✓
- MAE
- 0.03255✓
- MGE
- 0.04282
- MAE
- 0.04616
- MGE
- 0.09893
- MAE
- 0.09053
- MGE
- 0.09621✓
- MAE
- 0.08122✓
- MGE
- 0.04061
- MAE
- 0.02781
- MGE
- 0.03614✓
- MAE
- 0.02544✓
- MGE
- 0.05858✓
- MAE
- 0.02035✓
- MGE
- 0.06173
- MAE
- 0.03064
Photo by Lars Bo Nielsen on Unsplash
- MGE
- 0.09775
- MAE
- 0.11268✓
- MGE
- 0.09742✓
- MAE
- 0.11286
Photo by Mayer Tawfik on Unsplash
- MGE
- 0.03523✓
- MAE
- 0.02607✓
- MGE
- 0.03691
- MAE
- 0.03427
- MGE
- 0.02820✓
- MAE
- 0.02370
- MGE
- 0.02867
- MAE
- 0.02323✓
- MGE
- 0.04968✓
- MAE
- 0.03139✓
- MGE
- 0.05066
- MAE
- 0.03508
Photo by Niko Tsviliov on Unsplash
- MGE
- 0.26436
- MAE
- 0.22743
- MGE
- 0.25126✓
- MAE
- 0.18707✓
Photo by Norbert Braun on Unsplash
- MGE
- 0.05312✓
- MAE
- 0.08202✓
- MGE
- 0.06003
- MAE
- 0.10303
- MGE
- 0.07998✓
- MAE
- 0.29806✓
- MGE
- 0.08134
- MAE
- 0.31521
- MGE
- 0.05827
- MAE
- 0.10070
- MGE
- 0.05822✓
- MAE
- 0.09896✓
- MGE
- 0.04397✓
- MAE
- 0.05425✓
- MGE
- 0.06563
- MAE
- 0.30656
- MGE
- 0.04300
- MAE
- 0.07894✓
- MGE
- 0.04015✓
- MAE
- 0.08022
- MGE
- 0.36861
- MAE
- 0.49657
- MGE
- 0.36428✓
- MAE
- 0.48379✓
- MGE
- 0.06347✓
- MAE
- 0.03625✓
- MGE
- 0.06854
- MAE
- 0.05066
- MGE
- 0.02008✓
- MAE
- 0.01485✓
- MGE
- 0.02268
- MAE
- 0.01677
- MGE
- 0.03800✓
- MAE
- 0.01532✓
- MGE
- 0.03923
- MAE
- 0.02272
- MGE
- 0.06015✓
- MAE
- 0.14384
- MGE
- 0.06267
- MAE
- 0.12973✓
- MGE
- 0.03059✓
- MAE
- 0.04455✓
- MGE
- 0.03479
- MAE
- 0.07184
- MGE
- 0.03554✓
- MAE
- 0.00845✓
- MGE
- 0.03858
- MAE
- 0.01002
- MGE
- 0.02402✓
- MAE
- 0.00790✓
- MGE
- 0.02480
- MAE
- 0.00904
- MGE
- 0.03196✓
- MAE
- 0.02429✓
- MGE
- 0.03431
- MAE
- 0.03237
- MGE
- 0.07269
- MAE
- 0.05231
- MGE
- 0.05584✓
- MAE
- 0.00980✓
- MGE
- 0.04327
- MAE
- 0.02803
- MGE
- 0.03782✓
- MAE
- 0.01914✓
- MGE
- 0.06458
- MAE
- 0.10452
- MGE
- 0.05506✓
- MAE
- 0.07337✓
- MGE
- 0.41585
- MAE
- 0.46956✓
- MGE
- 0.41168✓
- MAE
- 0.54891
- MGE
- 0.07450✓
- MAE
- 0.05224✓
- MGE
- 0.07959
- MAE
- 0.06058
- MGE
- 0.16225✓
- MAE
- 0.11610
- MGE
- 0.16708
- MAE
- 0.10251✓
- MGE
- 0.08913✓
- MAE
- 0.03994✓
- MGE
- 0.10879
- MAE
- 0.28166
- MGE
- 0.10358✓
- MAE
- 0.04381✓
- MGE
- 0.11628
- MAE
- 0.08958
- MGE
- 0.01533✓
- MAE
- 0.03680
- MGE
- 0.01588
- MAE
- 0.03647✓
Photo by Vinicius Wiesehofer on Unsplash
- MGE
- 0.05919
- MAE
- 0.71899
- MGE
- 0.05785✓
- MAE
- 0.71783✓
- MGE
- 0.05586
- MAE
- 0.28043✓
- MGE
- 0.04380✓
- MAE
- 0.37341
- MGE
- 0.04125
- MAE
- 0.02597
- MGE
- 0.03718✓
- MAE
- 0.02069✓
- MGE
- 0.04612
- MAE
- 0.07316
- MGE
- 0.04383✓
- MAE
- 0.04392✓
- MGE
- 0.07274✓
- MAE
- 0.23800✓
- MGE
- 0.07506
- MAE
- 0.24634
- MGE
- 0.02746✓
- MAE
- 0.02864✓
- MGE
- 0.02951
- MAE
- 0.03488
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.