mlsanityData to 14 Oct 2026

GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields

arXiv 2407.05597 ↗First posted 8 Jul 2024cs.CV cs.GRcited by 6

Not on the map. Why?

Abstract (arXiv)

Although recent efforts have extended Neural Radiance Fields (NeRF) into LiDAR point cloud synthesis, the majority of existing works exhibit a strong dependence on precomputed poses. However, point cloud registration methods struggle to achieve precise global pose estimation, whereas previous pose-free NeRFs overlook geometric consistency in global reconstruction. In light of this, we explore the geometric insights of point clouds, which provide explicit registration priors for reconstruction. Based on this, we propose Geometry guided Neural LiDAR Fields(GeoNLF), a hybrid framework performing alternately global neural reconstruction and pure geometric pose optimization. Furthermore, NeRFs tend to overfit individual frames and easily get stuck in local minima under sparse-view inputs. To tackle this issue, we develop a selective-reweighting strategy and introduce geometric constraints for robust optimization. Extensive experiments on NuScenes and KITTI-360 datasets demonstrate the superiority of GeoNLF in both novel view synthesis and multi-view registration of low-frequency large-scale point clouds.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 51 of its 71 references that are in the map. First posted on arXiv 8 Jul 2024.

Builds on

51 of 71 references.

References · 51

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  5. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  7. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  8. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  9. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  10. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  11. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  12. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
38 more
  1. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  2. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  3. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  4. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  5. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  6. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  7. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
  8. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 297
  9. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  10. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 233
  11. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
  12. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  13. 2023Robust Dynamic Radiance Fieldscited by 194
  14. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 192
  15. 2023Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fieldscited by 143
  16. 2020LiDARsim: Realistic LiDAR Simulation by Leveraging the Real Worldcited by 137
  17. 2020Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondencescited by 109
  18. 2020DeepGMR: Learning Latent Gaussian Mixture Models for Registrationcited by 91
  19. 2020Learning multiview 3D point cloud registrationcited by 78
  20. 2023Neural LiDAR Fields for Novel View Synthesiscited by 67
  21. 2023DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fieldscited by 60
  22. 2022Parallel Inversion of Neural Radiance Fields for Robust Pose Estimationcited by 55
  23. 2023CamP: Camera Preconditioning for Neural Radiance Fieldscited by 55
  24. 2021HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registrationcited by 48
  25. 2023LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fieldscited by 47
  26. 2023NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fieldscited by 44
  27. 2023NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mappingcited by 41
  28. 2024LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesiscited by 27
  29. 2019Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytopecited by 26
  30. 2022Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolationcited by 26
  31. 2023Robust Camera Pose Refinement for Multi-Resolution Hash Encodingcited by 21
  32. 2022PCGen: Point Cloud Generator for LiDAR Simulationcited by 20
  33. 2023Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweightingcited by 19
  34. 2022Learning to Simulate Realistic LiDARscited by 16
  35. 2023SC-NeRF: Self-Correcting Neural Radiance Field with Sparse Viewscited by 14
  36. 2024Multiway Point Cloud Mosaicking with Diffusion and Global Optimizationcited by 14
  37. 2023Rotation Synchronization via Deep Matrix Factorizationcited by 7
  38. 2017CAD Priors for Accurate and Flexible Instance Reconstructioncited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025RealEngine: Simulating Autonomous Driving in Realistic Contextcited by 10
  2. 2026Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstructioncited by 2
  3. 2025Physically Based Neural LiDAR Resimulationcited by 1
  4. 2025LiDARDraft: Generating LiDAR Point Cloud from Versatile Inputscited by 1
  5. 2025Neural-MMGS: Multi-modal Neural Gaussian Splats for Large-Scale Scene Reconstructioncited by 0
  6. 2026Spectral-Geometric Neural Fields for Pose-Free LiDAR View Synthesiscited by 0