3D Semantic Scene Completion: a Survey

12 Mar 2021  ·  Luis Roldao, Raoul de Charette, Anne Verroust-Blondet ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
3D Semantic Scene Completion NYUv2 EdgeNet (SUNCG pretraining) mIoU 33.7 # 11
3D Semantic Scene Completion NYUv2 VD-CRF: Semantic scene completion with dense CRF from a single depth image. (SUNCG pretraining) mIoU 31.8 # 15
3D Semantic Scene Completion NYUv2 Real-time semantic scene completion via feature aggregation and conditioned prediction mIoU 34.4 # 9
3D Semantic Scene Completion NYUv2 Am2fnet: Attention-based multiscale & multi-modality fused network mIoU 31.7 # 16
3D Semantic Scene Completion NYUv2 3D semantic scene completion from a single depth image using adversarial training mIoU 22.7 # 27

Methods


No methods listed for this paper. Add relevant methods here