mlsanityData to 14 Oct 2026

SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving

arXiv 2306.09001 ↗First posted 15 Jun 2023cs.CVcited by 75

Not on the map. Why?

Abstract (arXiv)

Monocular scene understanding is a foundational component of autonomous systems. Within the spectrum of monocular perception topics, one crucial and useful task for holistic 3D scene understanding is semantic scene completion (SSC), which jointly completes semantic information and geometric details from RGB input. However, progress in SSC, particularly in large-scale street views, is hindered by the scarcity of high-quality datasets. To address this issue, we introduce SSCBench, a comprehensive benchmark that integrates scenes from widely used automotive datasets (e.g., KITTI-360, nuScenes, and Waymo). SSCBench follows an established setup and format in the community, facilitating the easy exploration of SSC methods in various street views. We benchmark models using monocular, trinocular, and point cloud input to assess the performance gap resulting from sensor coverage and modality. Moreover, we have unified semantic labels across diverse datasets to simplify cross-domain generalization testing. We commit to including more datasets and SSC models to drive further advancements in this field.

Key facts. Cited by 75 papers in the map (data through 14 Oct 2026). Builds on 77 of its 98 references that are in the map. First posted on arXiv 15 Jun 2023.

Builds on

77 of 98 references.

References · 77

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  4. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  5. 2022Planning-oriented Autonomous Drivingcited by 1,087
  6. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  7. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  8. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  9. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  10. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  11. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 537
  12. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
38 more
  1. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  2. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  3. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  4. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  5. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 336
  6. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 332
  7. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  8. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  9. 2021OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communicationcited by 304
  10. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  11. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 281
  12. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  13. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  14. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 221
  15. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  16. 2021Learning Distilled Collaboration Graph for Multi-Agent Perceptioncited by 194
  17. 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 190
  18. 2020A2D2: Audi Autonomous Driving Datasetcited by 190
  19. 2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 190
  20. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 188
  21. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  22. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 166
  23. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  24. 2022V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Drivingcited by 157
  25. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 156
  26. 2023V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perceptioncited by 155
  27. 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 153
  28. 2022Vision-Centric BEV Perception: A Surveycited by 126
  29. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  30. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  31. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 117
  32. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  33. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  34. 2023Street-View Image Generation from a Bird's-Eye View Layoutcited by 102
  35. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  36. 2022MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queriescited by 91
  37. 2020Canadian Adverse Driving Conditions Datasetcited by 87
  38. 2020LiDAR-based Panoptic Segmentation via Dynamic Shifting Networkcited by 84

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 19; 2025: 31; 2026: 19.

75 papers.

Sort:

By area:

  1. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 157
  2. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 90
  3. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 86
  4. 20253D and 4D World Modeling: A Surveycited by 67
  5. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 66
  6. 2024Context and Geometry Aware Voxel Transformer for Semantic Scene Completioncited by 50
  7. 2023OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environmentscited by 41
  8. 2023Camera-based 3D Semantic Scene Completion with Sparse Guidance Networkcited by 40
  9. 2024Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehiclescited by 33
  10. 2024RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radarcited by 33
  11. 2023DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptationcited by 32
  12. 2023S4C: Self-Supervised Semantic Scene Completion with Neural Fieldscited by 28
38 more
  1. 2024CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Predictioncited by 24
  2. 2023LiDAR-based 4D Occupancy Completion and Forecastingcited by 23
  3. 2024The RoboDrive Challenge: Drive Anytime Anywhere in Any Conditioncited by 23
  4. 2025QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Predictioncited by 20
  5. 2024Multiagent Multitraversal Multimodal Self-Driving: Open MARS Datasetcited by 18
  6. 2025GaussRender: Learning 3D Occupancy with Gaussian Renderingcited by 18
  7. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Modelscited by 16
  8. 2025VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detectioncited by 13
  9. 2025Feed-Forward SceneDINO for Unsupervised Semantic Scene Completioncited by 13
  10. 2024Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Drivingcited by 12
  11. 2024TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sightcited by 12
  12. 2025HiMo: High-Speed Objects Motion Compensation in Point Cloudscited by 12
  13. 2025GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splattingcited by 11
  14. 2024Label-efficient Semantic Scene Completion with Scribble Annotationscited by 9
  15. 2024PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Drivingcited by 9
  16. 2024LOMA: Language-assisted Semantic Occupancy Network via Triplane Mambacited by 8
  17. 2025L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Modelcited by 8
  18. 2025OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Cameracited by 8
  19. 2025Towards Learning to Complete Anything in Lidarcited by 7
  20. 2025Disentangling Instance and Scene Contexts for 3D Semantic Scene Completioncited by 7
  21. 2025VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regionscited by 7
  22. 2026OccAny: Generalized Unconstrained Urban 3D Occupancycited by 6
  23. 2025Automated Vehicles Should be Connected with Natural Languagecited by 5
  24. 2025OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspectivecited by 5
  25. 2026Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robotscited by 5
  26. 2024Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completioncited by 4
  27. 2026ChainFlow-VLA: Causal Flow Planning with Vision-Language Modelscited by 4
  28. 2025Event-aided Semantic Scene Completioncited by 3
  29. 2025SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completioncited by 3
  30. 2025IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposalscited by 3
  31. 2025One Step Closer: Creating the Future to Boost Monocular Semantic Scene Completioncited by 3
  32. 2025Vision-Only Gaussian Splatting for Collaborative Semantic Occupancy Predictioncited by 3
  33. 2025Enhancing 3D Semantic Scene Completion with a Refinement Modulecited by 3
  34. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  35. 2025Unleashing Semantic and Geometric Priors for 3D Scene Completioncited by 2
  36. 2026Exploring Easy Boosts for Lidar Semantic Scene Completioncited by 2
  37. 2024VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Predictioncited by 1
  38. 2025S2GO: Streaming Sparse Gaussian Occupancy Predictioncited by 1

50 most cited of 75 All 75 (JSON)