Research Article
Adaptive CU Split Decision Based on Deep Learning and Multifeature Fusion for H.266/VVC
Table 3
The classification probability of the texture classification model.
| Test sequence | | Level (%) | Depth = 0 | Depth = 1 | Depth = 2 | Depth = 3 |
| Class B (1920 × 1080) | ParkScene | 5.35 | 7.12 | 8.24 | 9.37 | Cactus | 4.13 | 6.22 | 5.68 | 5.18 |
| Class C (832 × 480) | BQMall | 2.14 | 4.95 | 5.12 | 6.3 | PartyScene | — | 4.21 | 4.62 | 4.99 |
| Class D (416 × 240) | BasketballPass | — | 6.76 | 5.81 | 4.75 | RaceHorses | — | 5.11 | 6.15 | 7.04 | | Average | 3.87 | 5.73 | 5.94 | 6.37 |
|
|