| 3d-semantic-scene-completion-on-nyuv2 | 3D semantic scene completion
from a single depth image using adversarial training | – | mIoU: 22.7 |
| 3d-semantic-scene-completion-on-nyuv2 | Am2fnet: Attention-based multiscale
& multi-modality fused network | – | mIoU: 31.7 |
| 3d-semantic-scene-completion-on-nyuv2 | EdgeNet (SUNCG pretraining) | – | mIoU: 33.7 |
| 3d-semantic-scene-completion-on-nyuv2 | Real-time semantic scene completion via feature aggregation and conditioned prediction | – | mIoU: 34.4 |
| 3d-semantic-scene-completion-on-nyuv2 | VD-CRF: Semantic scene completion with dense
CRF from a single depth image. (SUNCG pretraining) | – | mIoU: 31.8 |