mlsanityData to 14 Oct 2026

READ: Large-Scale Neural Scene Rendering for Autonomous Driving

arXiv 2205.05509 ↗First posted 11 May 2022cs.CV cs.AIcited by 51

Not on the map. Why?

Abstract (arXiv)

Synthesizing free-view photo-realistic images is an important task in multimedia. With the development of advanced driver assistance systems~(ADAS) and their applications in autonomous vehicles, experimenting with different scenarios becomes a challenge. Although the photo-realistic street scenes can be synthesized by image-to-image translation methods, which cannot produce coherent scenes due to the lack of 3D information. In this paper, a large-scale neural rendering method is proposed to synthesize the autonomous driving scene~(READ), which makes it possible to synthesize large-scale driving scenarios on a PC through a variety of sampling schemes. In order to represent driving scenarios, we propose an ω rendering network to learn neural descriptors from sparse point clouds. Our model can not only synthesize realistic driving scenes but also stitch and edit driving scenes. Experiments show that our model performs well in large-scale driving scenarios.

Key facts. Cited by 51 papers in the map (data through 14 Oct 2026). Builds on 23 of its 38 references that are in the map. First posted on arXiv 11 May 2022.

Builds on

23 of 38 references.

References · 23

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  5. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  6. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  7. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  8. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  9. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  10. 2019Neural Point-Based Graphicscited by 327
  11. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 326
  12. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
11 more
  1. 2019Neural Rerendering in the Wildcited by 121
  2. 2019Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generationcited by 75
  3. 2021Enhancing Photorealism Enhancementcited by 74
  4. 2021Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesiscited by 56
  5. 2020Dual Attention GANs for Semantic Image Synthesiscited by 41
  6. 2021End-to-End Video Object Detection with Spatial-Temporal Transformerscited by 40
  7. 2021Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detectioncited by 33
  8. 2019Brno Urban Dataset -- The New Data for Self-Driving Agents and Mapping Taskscited by 19
  9. 2021iButter: Neural Interactive Bullet Time Generator for Human Free-viewpoint Renderingcited by 16
  10. 2020TRANSPR: Transparency Ray-Accumulating Neural 3D Scene Point Renderercited by 9
  11. 2021Few-shot Neural Human Performance Rendering from Sparse RGBD Videoscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 21; 2024: 20; 2025: 7; 2026: 2.

51 papers.

Sort:

By area:

  1. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 221
  2. 2023Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Renderingcited by 143
  3. 2023StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Viewscited by 120
  4. 2023Human Gaussian Splatting: Real-time Rendering of Animatable Avatarscited by 105
  5. 2024Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agentscited by 91
  6. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  7. 2023Urban Radiance Field Representation with Deformable Neural Mesh Primitivescited by 55
  8. 2023Real-Time Neural Rasterization for Large Scenescited by 37
  9. 2023Towards Knowledge-driven Autonomous Drivingcited by 29
  10. 2024LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitivescited by 26
  11. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  12. 2024UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Setscited by 23
38 more
  1. 2023RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representationcited by 20
  2. 2024Neural Radiance Field in Autonomous Driving: A Surveycited by 19
  3. 2024AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesiscited by 17
  4. 2024GGS: Generalizable Gaussian Splatting for Lane Switching in Autonomous Drivingcited by 17
  5. 2024HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenescited by 16
  6. 2023MapNeRF: Incorporating Map Priors into Neural Radiance Fields for Driving View Simulationcited by 15
  7. 2024From Chaos to Clarity: 3DGS in the Darkcited by 15
  8. 2023Applications of Large Scale Foundation Models for Autonomous Drivingcited by 14
  9. 2024EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encodingcited by 13
  10. 20233D Data Augmentation for Driving Scenes on Cameracited by 12
  11. 2022Boosting Point Clouds Rendering via Radiance Mappingcited by 11
  12. 2023Frequency-Modulated Point Cloud Rendering with Easy Editingcited by 10
  13. 2023DGNR: Density-Guided Neural Point Rendering of Large Driving Scenescited by 9
  14. 2025Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Surveycited by 9
  15. 2023Interactive Geometry Editing of Neural Radiance Fieldscited by 7
  16. 2023HarmonicNeRF: Geometry-Informed Synthetic View Augmentation for 3D Scene Reconstruction in Driving Scenarioscited by 7
  17. 2024Efficient Depth-Guided Urban View Synthesiscited by 7
  18. 2024XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifoldcited by 6
  19. 2024ClusteringSDF: Self-Organized Neural Implicit Surfaces for 3D Decompositioncited by 5
  20. 2024RPBG: Towards Robust Neural Point-based Graphics in the Wildcited by 5
  21. 2024SpecGaussian with Latent Features: A High-quality Modeling of the View-dependent Appearance for 3D Gaussian Splattingcited by 5
  22. 2024GaRField++: Reinforced Gaussian Radiance Fields for Large-Scale 3D Scene Reconstructioncited by 5
  23. 2023AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimizationcited by 4
  24. 2023Instant Photorealistic Neural Radiance Fields Stylizationcited by 3
  25. 2023SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Imagecited by 2
  26. 2023FG-NeRF: Flow-GAN based Probabilistic Neural Radiance Field for Independence-Assumption-Free Uncertainty Estimationcited by 2
  27. 2024NeRO: Neural Road Surface Reconstructioncited by 1
  28. 2025sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Viewscited by 1
  29. 2025CE-NPBG: Connectivity Enhanced Neural Point-Based Graphics for Novel View Synthesis in Autonomous Driving Scenescited by 1
  30. 2025DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splattingcited by 1
  31. 2026FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Modelcited by 1
  32. 2023Enhance-NeRF: Multiple Performance Evaluation for Neural Radiance Fieldscited by 0
  33. 2023Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehiclecited by 0
  34. 2024Data-driven Camera and Lidar Simulation Models for Autonomous Driving: A Review from Generative Models to Volume Rendererscited by 0
  35. 2024NARVis: Neural Accelerated Rendering for Real-Time Scientific Point Cloud Visualizationcited by 0
  36. 2025K-Buffers: A Plug-in Method for Enhancing Neural Fields with Multiple Bufferscited by 0
  37. 2025Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRFcited by 0
  38. 2025SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understandingcited by 0

50 most cited of 51 All 51 (JSON)