3D Semantic Scene Completion: a Survey
Luis Roldao, Raoul de Charette, Anne Verroust-Blondet
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the multiplication of large-scale 3D datasets, SSC has gained significant momentum in the research community because it holds unresolved challenges. Specifically, SSC lies in the ambiguous completion of large unobserved areas and the weak supervision signal of the ground truth. This led to a substantially increasing number of papers on the matter. This survey aims to identify, compare and analyze the techniques providing a critical analysis of the SSC literature on both methods and datasets. Throughout the paper, we provide an in-depth analysis of the existing works covering all choices made by the authors while highlighting the remaining avenues of research. SSC performance of the SoA on the most popular datasets is also evaluated and analyzed.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| NYUv2 | Real-time semantic scene completion via feature aggregation and conditioned prediction | mIoU | 34.4 | — | Unverified |
| NYUv2 | EdgeNet (SUNCG pretraining) | mIoU | 33.7 | — | Unverified |
| NYUv2 | VD-CRF: Semantic scene completion with dense CRF from a single depth image. (SUNCG pretraining) | mIoU | 31.8 | — | Unverified |
| NYUv2 | Am2fnet: Attention-based multiscale & multi-modality fused network | mIoU | 31.7 | — | Unverified |
| NYUv2 | 3D semantic scene completion from a single depth image using adversarial training | mIoU | 22.7 | — | Unverified |