mlsanityData to 7 Oct 2026

Occupancy as Set of Points

arXiv 2407.04049 ↗First posted 4 Jul 2024cs.CV cs.ROcited by 37

Not on the map. Why?

Abstract (arXiv)

In this paper, we explore a novel point representation for 3D occupancy prediction from multi-view images, which is named Occupancy as Set of Points. Existing camera-based methods tend to exploit dense volume-based representation to predict the occupancy of the whole scene, making it hard to focus on the special areas or areas out of the perception range. In comparison, we present the Points of Interest (PoIs) to represent the scene and propose OSP, a novel framework for point-based 3D occupancy prediction. Owing to the inherent flexibility of the point-based representation, OSP achieves strong performance compared with existing methods and excels in terms of training and inference adaptability. It extends beyond traditional perception boundaries and can be seamlessly integrated with volume-based methods to significantly enhance their effectiveness. Experiments on the Occ3D nuScenes occupancy benchmark show that OSP has strong performance and flexibility. Code and models are available at urlhttps://github.com/hustvl/osp.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 28 of its 34 references that are in the map. First posted on arXiv 4 Jul 2024.

Builds on

28 of 34 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  5. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  6. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  7. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  8. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  9. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  10. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  11. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  12. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
16 more
  1. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  2. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  3. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  4. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  5. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  6. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 187
  7. 2020Anisotropic Convolutional Networks for 3D Semantic Scene Completioncited by 126
  8. 20203D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Priorcited by 124
  9. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 88
  10. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 85
  11. 2019Efficient Semantic Scene Completion Network with Spatial Group Convolutioncited by 66
  12. 2019RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completioncited by 54
  13. 2021Semantic Scene Completion via Integrating Instances and Scene in-the-Loopcited by 54
  14. 2023PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Predictioncited by 51
  15. 2019Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completioncited by 43
  16. 2020Depth Based Semantic Scene Completion with Position Importance Aware Losscited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 16; 2026: 12.

37 papers.

Sort:

By area:

  1. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 83
  2. 2024GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Predictioncited by 66
  3. 2024GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understandingcited by 46
  4. 2025GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flowcited by 24
  5. 2025STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Predictioncited by 20
  6. 2025DVGT: Driving Visual Geometry Transformercited by 20
  7. 2024ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictionscited by 19
  8. 2025QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Predictioncited by 19
  9. 2024An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Trainingcited by 17
  10. 2024Deep Height Decoupling for Precise Vision-based 3D Occupancy Predictioncited by 16
  11. 2024DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Predictioncited by 15
  12. 2025AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splattingcited by 14
25 more
  1. 2025AGO: Adaptive Grounding for Open World 3D Occupancy Predictioncited by 9
  2. 2025Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Predictioncited by 9
  3. 2026Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Predictioncited by 9
  4. 2025Semantic Causality-Aware Vision-Based 3D Occupancy Predictioncited by 8
  5. 2024LightOcc: Lightweight Spatial Embedding for Efficient Vision-based 3D Occupancy Predictioncited by 6
  6. 2024GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splattingcited by 6
  7. 2025ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimationcited by 6
  8. 2026OccAny: Generalized Unconstrained Urban 3D Occupancycited by 6
  9. 2026Monocular Open Vocabulary Occupancy Prediction for Indoor Scenescited by 5
  10. 2025SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Drivingcited by 4
  11. 2025VG3T: Visual Geometry Grounded Gaussian Transformercited by 4
  12. 2025Event-aided Semantic Scene Completioncited by 3
  13. 2026AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environmentscited by 3
  14. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  15. 2026Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Drivingcited by 2
  16. 2026FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Predictioncited by 2
  17. 2026O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Embodied Intelligent Roboticscited by 1
  18. 2025Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlationcited by 0
  19. 2025DSOcc: Leveraging Depth Awareness and Semantic Aid to Boost Camera-Based 3D Semantic Occupancy Predictioncited by 0
  20. 2025From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Predictioncited by 0
  21. 2026SuperOcc: Toward Cohesive Temporal Modeling for Superquadric-based 3D Occupancy Predictioncited by 0
  22. 2026Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillationcited by 0
  23. 2026UnsOcc: 3D Semantic Occupancy Prediction in Unstructured Scene via Rendering Fusioncited by 0
  24. 2026GPOcc++: Unified Sparse Gaussian Occupancy Prediction with Visual Geometry Priorscited by 0
  25. 2026RayOcc: Occlusion-Aware Ray Occupancy Estimation via Gaussian Mixture Intensitycited by 0