Context-Aware Matting
Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Computer Vision4 results
- MSE· 2019-09-20SOTA8.2best: 2.26 (DiffMatte)
- Conn· 2019-09-2033.2best: 50.8 (DIM)
- Grad· 2019-09-2017.3best: 31 (DIM)
- SAD· 2019-09-2035.8best: 46.22 (PP-Matting)