TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/3D Semantic Scene Completion: a Survey

3D Semantic Scene Completion: a Survey

Luis Roldao, Raoul de Charette, Anne Verroust-Blondet

2021-03-123D Semantic Segmentation3D Semantic Scene Completion
PaperPDF

Abstract

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.

Results

TaskDatasetMetricValueModel
3D ReconstructionNYUv2mIoU34.4Real-time semantic scene completion via feature aggregation and conditioned prediction
3D ReconstructionNYUv2mIoU33.7EdgeNet (SUNCG pretraining)
3D ReconstructionNYUv2mIoU31.8VD-CRF: Semantic scene completion with dense CRF from a single depth image. (SUNCG pretraining)
3D ReconstructionNYUv2mIoU31.7Am2fnet: Attention-based multiscale & multi-modality fused network
3D ReconstructionNYUv2mIoU22.73D semantic scene completion from a single depth image using adversarial training
3DNYUv2mIoU34.4Real-time semantic scene completion via feature aggregation and conditioned prediction
3DNYUv2mIoU33.7EdgeNet (SUNCG pretraining)
3DNYUv2mIoU31.8VD-CRF: Semantic scene completion with dense CRF from a single depth image. (SUNCG pretraining)
3DNYUv2mIoU31.7Am2fnet: Attention-based multiscale & multi-modality fused network
3DNYUv2mIoU22.73D semantic scene completion from a single depth image using adversarial training
3D Semantic Scene CompletionNYUv2mIoU34.4Real-time semantic scene completion via feature aggregation and conditioned prediction
3D Semantic Scene CompletionNYUv2mIoU33.7EdgeNet (SUNCG pretraining)
3D Semantic Scene CompletionNYUv2mIoU31.8VD-CRF: Semantic scene completion with dense CRF from a single depth image. (SUNCG pretraining)
3D Semantic Scene CompletionNYUv2mIoU31.7Am2fnet: Attention-based multiscale & multi-modality fused network
3D Semantic Scene CompletionNYUv2mIoU22.73D semantic scene completion from a single depth image using adversarial training

Related Papers

Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion2025-07-11LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds2025-06-09GS4: Generalizable Sparse Splatting Semantic SLAM2025-06-06Point-MoE: Towards Cross-Domain Generalization in 3D Semantic Segmentation via Mixture-of-Experts2025-05-29seg_3D_by_PC2D: Multi-View Projection for Domain Generalization and Adaptation in 3D Semantic Segmentation2025-05-21Camera-Only 3D Panoptic Scene Completion for Autonomous Driving through Differentiable Object Shapes2025-05-14MFSeg: Efficient Multi-frame 3D Semantic Segmentation2025-05-073D Can Be Explored In 2D: Pseudo-Label Generation for LiDAR Point Clouds Using Sensor-Intensity-Based 2D Semantic Segmentation2025-05-06