mlsanityData to 7 Oct 2026

S-NeRF: Neural Radiance Fields for Street Views

arXiv 2303.00749 ↗First posted 1 Mar 2023cs.CVcited by 116

Not on the map. Why?

Abstract (arXiv)

Neural Radiance Fields (NeRFs) aim to synthesize novel views of objects and scenes, given the object-centric camera views with large overlaps. However, we conjugate that this paradigm does not fit the nature of the street views that are collected by many self-driving cars from the large-scale unbounded scenes. Also, the onboard cameras perceive scenes without much overlapping. Thus, existing NeRFs often produce blurs, 'floaters' and other artifacts on street-view synthesis. In this paper, we propose a new street-view NeRF (S-NeRF) that considers novel view synthesis of both the large-scale background scenes and the foreground moving vehicles jointly. Specifically, we improve the scene parameterization function and the camera poses for learning better neural representations from street views. We also use the the noisy and sparse LiDAR points to boost the training and learn a robust geometry and reprojection based confidence to address the depth outliers. Moreover, we extend our S-NeRF for reconstructing moving vehicles that is impracticable for conventional NeRFs. Thorough experiments on the large-scale driving datasets (e.g., nuScenes and Waymo) demonstrate that our method beats the state-of-the-art rivals by reducing 7% to 40% of the mean-squared error in the street-view synthesis and a 45% PSNR gain for the moving vehicles rendering.

Key facts. Cited by 116 papers in the map (data through 7 Oct 2026). Builds on 41 of its 53 references that are in the map. First posted on arXiv 1 Mar 2023.

Builds on

41 of 53 references.

References · 41

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  7. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  9. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  10. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  11. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  12. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
29 more
  1. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  2. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  3. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  4. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  5. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  6. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  7. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  8. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  9. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  10. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  11. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  12. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  13. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  14. 2021Urban Radiance Fieldscited by 263
  15. 2018Video Based Reconstruction of 3D People Modelscited by 237
  16. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  17. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  18. 2017Learning a Multi-View Stereo Machinecited by 194
  19. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  20. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
  21. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  22. 2020DeRF: Decomposed Radiance Fieldscited by 163
  23. 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
  24. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  25. 2021Animatable Neural Radiance Fields from Monocular RGB Videoscited by 109
  26. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  27. 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
  28. 2021GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Drivingcited by 75
  29. 2020From Points to Multi-Object 3D Reconstructioncited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 25; 2024: 51; 2025: 27; 2026: 13.

116 papers.

Sort:

By area:

  1. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
  2. 2024A Survey on 3D Gaussian Splattingcited by 221
  3. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  4. 2023MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Drivingcited by 170
  5. 2023NeuRAD: Neural Rendering for Autonomous Drivingcited by 146
  6. 2023Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Renderingcited by 143
  7. 2024DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representationcited by 123
  8. 2023StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Viewscited by 120
  9. 2024textitS3Gaussian: Self-Supervised Street Gaussians for Autonomous Drivingcited by 105
  10. 2023WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generationcited by 93
  11. 2024Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agentscited by 91
  12. 2024ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restorationcited by 89
38 more
  1. 2024MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenescited by 70
  2. 2024SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Drivingcited by 66
  3. 2023NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenescited by 53
  4. 2024STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenescited by 53
  5. 2024FreeVS: Generative View Synthesis on Free Driving Trajectorycited by 52
  6. 2024Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splattingcited by 49
  7. 2023LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fieldscited by 46
  8. 2024DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenescited by 45
  9. 2023NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fieldscited by 44
  10. 20243DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Viewscited by 37
  11. 2024SGD: Street View Synthesis with Gaussian Splatting and Diffusion Priorcited by 36
  12. 2025ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representationcited by 36
  13. 2024Dynamic 3D Gaussian Fields for Urban Areascited by 35
  14. 2024The NeRFect Match: Exploring NeRF Features for Visual Localizationcited by 32
  15. 2024S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generationcited by 28
  16. 2024Multi-Level Neural Scene Graphs for Dynamic Urban Environmentscited by 27
  17. 2024DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Drivingcited by 27
  18. 2025Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environmentscited by 27
  19. 2024VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priorscited by 25
  20. 2025CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Drivingcited by 25
  21. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  22. 2023UC-NeRF: Neural Radiance Field for Under-Calibrated Multi-view Cameras in Autonomous Drivingcited by 23
  23. 2024Neural Fields in Robotics: A Surveycited by 21
  24. 2024Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gapcited by 20
  25. 2024SplatFlow: Self-Supervised Dynamic Gaussian Splatting in Neural Motion Flow Field for Autonomous Drivingcited by 20
  26. 2025EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesiscited by 20
  27. 2023MV-Map: Offboard HD-Map Generation with Multi-view Consistencycited by 19
  28. 2024AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesiscited by 17
  29. 2024HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenescited by 16
  30. 2024NeRFs in Robotics: A Surveycited by 16
  31. 2024DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videoscited by 16
  32. 2023MapNeRF: Incorporating Map Priors into Neural Radiance Fields for Driving View Simulationcited by 15
  33. 20244D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitivescited by 15
  34. 2023Applications of Large Scale Foundation Models for Autonomous Drivingcited by 14
  35. 2024LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenescited by 14
  36. 2024EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splattingcited by 13
  37. 2023UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fieldscited by 12
  38. 2023Digging into Depth Priors for Outdoor Neural Radiance Fieldscited by 11

50 most cited of 116 All 116 (JSON)