Image Matting On Am 2K
평가 지표
MAD
MSE
SAD
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | MAD | MSE | SAD |
|---|---|---|---|
| a-late-fusion-cnn-for-digital-matting | 0.0210 | 0.0116 | 36.12 |
| end-to-end-animal-image-matting | 0.0064 | 0.0029 | 10.89 |
| end-to-end-animal-image-matting | 0.0060 | 0.0028 | 10.24 |
| end-to-end-animal-image-matting | 0.0059 | 0.0029 | 10.26 |
| semantic-human-matting | 0.0102 | 0.0068 | 17.81 |
| end-to-end-animal-image-matting | 0.0056 | 0.0024 | 9.66 |
| boosting-semantic-human-matting-with-coarse | 0.0356 | 0.0270 | 61.50 |
| adversarially-guided-portrait-matting | 0.0055 | 0.0024 | 9.602 |
| attention-guided-hierarchical-structure | 0.0161 | 0.0055 | 28.01 |