mlsanityData to 7 Oct 2026

Two Stream 3D Semantic Scene Completion

arXiv 1804.03550 ↗First posted 10 Apr 2018cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Inferring the 3D geometry and the semantic meaning of surfaces, which are occluded, is a very challenging task. Recently, a first end-to-end learning approach has been proposed that completes a scene from a single depth image. The approach voxelizes the scene and predicts for each voxel if it is occupied and, if it is occupied, the semantic class label. In this work, we propose a two stream approach that leverages depth information and semantic information, which is inferred from the RGB image, for this task. The approach constructs an incomplete 3D semantic tensor, which uses a compact three-channel encoding for the inferred semantic information, and uses a 3D CNN to infer the complete 3D semantic tensor. In our experimental evaluation, we show that the proposed two stream approach substantially outperforms the state-of-the-art for semantic scene completion.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 3; 2023: 15; 2024: 13; 2025: 3; 2026: 7.

48 papers.

Sort:

By area:

  1. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  2. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  3. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  4. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 85
  5. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  6. 20213D Semantic Scene Completion: a Surveycited by 74
  7. 2023AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformerscited by 65
  8. 2021Semantic Scene Completion via Integrating Instances and Scene in-the-Loopcited by 54
  9. 2024EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understandingcited by 43
  10. 2023PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awarenesscited by 42
  11. 2022MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environmentscited by 40
  12. 2021Semantic Segmentation-assisted Scene Completion for LiDAR Point Cloudscited by 37
36 more
  1. 2024Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completioncited by 32
  2. 2023SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusioncited by 30
  3. 2023DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptationcited by 30
  4. 2024OccMamba: Semantic Occupancy Prediction with State Space Modelscited by 29
  5. 2023Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Reviewcited by 25
  6. 2021Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspectivecited by 22
  7. 2023Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completioncited by 21
  8. 2023Semantic Scene Completion with Cleaner Selfcited by 12
  9. 2024TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sightcited by 12
  10. 2025VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detectioncited by 12
  11. 2022CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusioncited by 11
  12. 2024OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generationcited by 10
  13. 2021IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancementcited by 9
  14. 2021Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priorscited by 9
  15. 2024PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Drivingcited by 9
  16. 2024Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Predictioncited by 8
  17. 2025Towards Learning to Complete Anything in Lidarcited by 7
  18. 2022Point Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Imagecited by 6
  19. 2023Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequencecited by 6
  20. 2023CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completioncited by 4
  21. 2024V2VSSC: A 3D Semantic Scene Completion Benchmark for Perception with Vehicle to Vehicle Communicationcited by 4
  22. 2024Unleashing Network Potentials for Semantic Scene Completioncited by 4
  23. 2024Deep Learning for 3D Point Cloud Enhancement: A Surveycited by 4
  24. 2024MetaSSC: Enhancing 3D Semantic Scene Completion for Autonomous Driving through Meta-Learning and Long-sequence Modelingcited by 4
  25. 2023Real-time 3D Semantic Scene Completion Via Feature Aggregation and Conditioned Predictioncited by 3
  26. 2026Exploring Easy Boosts for Lidar Semantic Scene Completioncited by 2
  27. 2026Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Predictioncited by 1
  28. 2023P2M2-Net: Part-Aware Prompt-Guided Multimodal Point Cloud Completioncited by 0
  29. 2024DOCTR: Disentangled Object-Centric Transformer for Point Scene Understandingcited by 0
  30. 2024Towards Balanced RGB-TSDF Fusion for Consistent Semantic Scene Completion by 3D RGB Feature Completion and a Classwise Entropy Loss Functioncited by 0
  31. 2025Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlationcited by 0
  32. 2026SelfOccFlow: Towards end-to-end self-supervised 3D Occupancy Flow predictioncited by 0
  33. 2026EditSSC: Toward Editable Semantic Occupancy Scenes with Unconditional Diffusion Modelscited by 0
  34. 2026Semantic Occupancy Prediction with Dual Range-Voxel Representationcited by 0
  35. 2026SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completioncited by 0
  36. 2026AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Taskscited by 0