mlsanityData to 7 Oct 2026

OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments

arXiv 2312.09243 ↗First posted 14 Dec 2023cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

Occupancy prediction reconstructs 3D structures of surrounding environments. It provides detailed information for autonomous driving planning and navigation. However, most existing methods heavily rely on the LiDAR point clouds to generate occupancy ground truth, which is not available in the vision-based system. In this paper, we propose an OccNeRF method for training occupancy networks without 3D supervision. Different from previous works which consider a bounded scene, we parameterize the reconstructed occupancy fields and reorganize the sampling strategy to align with the cameras' infinite perceptive range. The neural rendering is adopted to convert occupancy fields to multi-camera depth maps, supervised by multi-frame photometric consistency. Moreover, for semantic occupancy prediction, we design several strategies to polish the prompts and filter the outputs of a pretrained open-vocabulary 2D segmentation model. Extensive experiments for both self-supervised depth estimation and 3D occupancy prediction tasks on nuScenes and SemanticKITTI datasets demonstrate the effectiveness of our method.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 93 of its 113 references that are in the map. First posted on arXiv 14 Dec 2023.

Builds on

93 of 113 references.

References · 93

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2023Segment Anythingcited by 8,158
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  6. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  7. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  8. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  9. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  10. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  11. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  12. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
38 more
  1. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  2. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  3. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  4. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  5. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  6. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  7. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  8. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  9. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  10. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  11. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  12. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  13. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  14. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  15. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  16. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  17. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  18. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  19. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  20. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  21. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  22. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  23. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  24. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  25. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  26. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 470
  27. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  28. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  29. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  30. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  31. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  32. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  33. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  34. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  35. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  36. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  37. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  38. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310

50 most cited of 93 All 93 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 14; 2026: 14.

39 papers.

Sort:

By area:

  1. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 139
  2. 2024OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Drivingcited by 76
  3. 2024Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentationcited by 34
  4. 2025Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Drivingcited by 29
  5. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  6. 2024Let Occ Flow: Self-Supervised 3D Occupancy Flow Predictioncited by 23
  7. 2024OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flowcited by 22
  8. 2024VEON: Vocabulary-Enhanced Occupancy Predictioncited by 22
  9. 2024PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priorscited by 21
  10. 2025DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Drivingcited by 20
  11. 2025GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Controlcited by 19
  12. 2024HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenescited by 16
27 more
  1. 2024Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Drivingcited by 12
  2. 2024Neural Radiance Field-based Visual Rendering: A Comprehensive Reviewcited by 12
  3. 2025GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splattingcited by 11
  4. 2025Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilitiescited by 6
  5. 2026OccAny: Generalized Unconstrained Urban 3D Occupancycited by 6
  6. 2025Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectivescited by 5
  7. 2025ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understandingcited by 3
  8. 2025Test-Time 3D Occupancy Predictioncited by 2
  9. 2025MinkOcc: Towards real-time label-efficient semantic occupancy predictioncited by 2
  10. 2025See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Predictioncited by 2
  11. 2025YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videoscited by 1
  12. 2026Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Imagescited by 1
  13. 2025Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlationcited by 0
  14. 2025OccLE: Label-Efficient 3D Semantic Occupancy Predictioncited by 0
  15. 2025HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Predictioncited by 0
  16. 2026SUG-Occ: Explicit Semantics and Uncertainty Guided Sparse Learning for Efficient 3D Occupancy Predictioncited by 0
  17. 2026Rebenchmarking Unsupervised Monocular 3D Occupancy Predictioncited by 0
  18. 2026Towards Learning a Generalizable 3D Scene Representation from 2D Observationscited by 0
  19. 2026Adaptive Multi-Scale Channel-Spatial Attention Aggregation Framework for 3D Indoor Semantic Scene Completion Toward Assisting Visually Impairedcited by 0
  20. 2026SelfOccFlow: Towards end-to-end self-supervised 3D Occupancy Flow predictioncited by 0
  21. 2026FreeOcc: Training-free Panoptic Occupancy Prediction via Foundation Modelscited by 0
  22. 2026RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Videocited by 0
  23. 2026Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillationcited by 0
  24. 2026Unsupervised Collaborative Domain Adaptation for Driving Scene Parsingcited by 0
  25. 2026VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Modelscited by 0
  26. 2026Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Drivingcited by 0
  27. 2026TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perceptioncited by 0