3D Semantic Scene Completion
This task was introduced in "Semantic Scene Completion from a Single Depth Image" (https://arxiv.org/abs/1611.08974) at CVPR 2017 . The target is to infer the dense 3D voxelized semantic scene from an incompleted 3D input (e.g. point cloud, depth map) and an optional RGB image. A recent summary can be found in the paper "3D Semantic Scene Completion: a Survey" (https://arxiv.org/abs/2103.07466), published at IJCV 2021.
Papers
Showing 1–10 of 65 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SG-SSC | mIoU | 55.4 | — | Unverified |
| 2 | SISNet | mIoU | 52.4 | — | Unverified |
| 3 | SPAwN (SUNCG pretraining) | mIoU | 49.9 | — | Unverified |
| 4 | SPAwN | mIoU | 48 | — | Unverified |
| 5 | Point-Voxel Aggregation Network | mIoU | 46 | — | Unverified |
| 6 | CCPNet (SUNCG pretraining) | mIoU | 41.3 | — | Unverified |
| 7 | 3DSketch | mIoU | 41.1 | — | Unverified |
| 8 | ForkNet (SUNCG pretraining) | mIoU | 37.1 | — | Unverified |
| 9 | IPF-SPCNet: Semantic point completion network for 3D semantic scene completion | mIoU | 35.1 | — | Unverified |
| 10 | Real-time semantic scene completion via feature aggregation and conditioned prediction | mIoU | 34.4 | — | Unverified |