mlsanityData to 7 Oct 2026

Neural Kernel Surface Reconstruction

arXiv 2305.19590 ↗First posted 31 May 2023cs.CVcited by 102

Not on the map. Why?

Abstract (arXiv)

We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud. Our approach builds upon the recently introduced Neural Kernel Fields (NKF) representation. It enjoys similar generalization capabilities to NKF, while simultaneously addressing its main limitations: (a) We can scale to large scenes through compactly supported kernel functions, which enable the use of memory-efficient sparse linear solvers. (b) We are robust to noise, through a gradient fitting solve. (c) We minimize training requirements, enabling us to learn from any dataset of dense oriented points, and even mix training data consisting of objects and scenes at different scales. Our method is capable of reconstructing millions of points in a few seconds, and handling very large scenes in an out-of-core fashion. We achieve state-of-the-art results on reconstruction benchmarks consisting of single objects, indoor scenes, and outdoor scenes.

Key facts. Cited by 102 papers in the map (data through 7 Oct 2026). Builds on 64 of its 88 references that are in the map. First posted on arXiv 31 May 2023.

Builds on

64 of 88 references.

References · 64

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  9. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  10. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  11. 2020Convolutional Occupancy Networkscited by 760
  12. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
38 more
  1. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  2. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  3. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  4. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  5. 2015Deep Kernel Learningcited by 440
  6. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  7. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  8. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  9. 2017Submanifold Sparse Convolutional Networkscited by 223
  10. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  11. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  12. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  13. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  14. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  15. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 182
  16. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  17. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  18. 2019CvxNet: Learnable Convex Decompositioncited by 173
  19. 2019NASA: Neural Articulated Shape Approximationcited by 149
  20. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  21. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  22. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  23. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  24. 20183D Point Capsule Networkscited by 106
  25. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  26. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  27. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  28. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  29. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  30. 2020Learning Deformable Tetrahedral Meshes for 3D Reconstructioncited by 84
  31. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  32. 2020DI-Fusion: Online Implicit 3D Reconstruction with Deep Priorscited by 70
  33. 2018MeshCNN: A Network with an Edgecited by 69
  34. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  35. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  36. 2020Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networkscited by 52
  37. 2020CaSPR: Learning Canonical Spatiotemporal Point Cloud Representationscited by 51
  38. 2022Critical Regularizations for Neural Surface Reconstruction in the Wildcited by 51

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 36; 2025: 45; 2026: 16.

102 papers.

Sort:

By area:

  1. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 183
  2. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  3. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 103
  4. 2024UniScene: Unified Occupancy-centric Driving Scene Generationcited by 102
  5. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 93
  6. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  7. 2025Visual Imitation Enables Contextual Humanoid Controlcited by 57
  8. 20244K4DGen: Panoramic 4D Generation at 4K Resolutioncited by 54
  9. 2024LidarDM: Generative LiDAR Simulation in a Generated Worldcited by 53
  10. 2024PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistencycited by 42
  11. 2024GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modelingcited by 30
  12. 2024G3R: Gradient Guided Generalizable Reconstructioncited by 29
38 more
  1. 2023Choose Your Simulator Wisely: A Review on Open-source Simulators for Autonomous Drivingcited by 26
  2. 2024LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesiscited by 26
  3. 2025GaussGym: An open-source real-to-sim framework for learning locomotion from pixelscited by 22
  4. 2025iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videoscited by 18
  5. 2025ORV: 4D Occupancy-centric Robot Video Generationcited by 16
  6. 2024Unsupervised Occupancy Learning from Sparse Point Cloudcited by 15
  7. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  8. 2025Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusioncited by 15
  9. 2025ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Graspingcited by 13
  10. 2024PoNQ: a Neural QEM-based Mesh Representationcited by 12
  11. 2024Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interactioncited by 12
  12. 2023Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Modelcited by 10
  13. 2025LiDPM: Rethinking Point Diffusion for Lidar Scene Completioncited by 10
  14. 2024Zero-Shot Multi-Object Scene Completioncited by 9
  15. 2024DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstructioncited by 8
  16. 20243D LiDAR Mapping in Dynamic Environments Using a 4D Implicit Neural Representationcited by 8
  17. 2025Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Methodcited by 8
  18. 2023DiViNeT: 3D Reconstruction from Disparate Views via Neural Template Regularizationcited by 7
  19. 2024Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefrontscited by 7
  20. 2024Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Cloudscited by 7
  21. 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priorscited by 7
  22. 2025SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splattingcited by 7
  23. 2025Sparfels: Fast Reconstruction from Sparse Unposed Imagerycited by 7
  24. 2025Anti-Aliased 2D Gaussian Splattingcited by 7
  25. 2024CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequencescited by 6
  26. 2025Parametric Point Cloud Completion for Polygonal Surface Reconstructioncited by 6
  27. 2024CoFie: Learning Compact Neural Surface Representations with Coordinate Fieldscited by 5
  28. 2024SweepNet: Unsupervised Learning Shape Abstraction via Neural Sweeperscited by 5
  29. 2024DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fittingcited by 5
  30. 2024Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversariescited by 5
  31. 2024Toward Robust Neural Reconstruction from Sparse Point Setscited by 5
  32. 2025Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splattingcited by 5
  33. 2025From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Imagescited by 5
  34. 2025InvRGB+L: Inverse Rendering of Complex Scenes with Unified Color and LiDAR Reflectance Modelingcited by 4
  35. 2024SMORE: Simultaneous Map and Object REconstructioncited by 3
  36. 2024PointDreamer: Zero-shot 3D Textured Mesh Reconstruction from Colored Point Cloudcited by 3
  37. 2024UMERegRobust - Universal Manifold Embedding Compatible Features for Robust Point Cloud Registrationcited by 3
  38. 2024Optimal Time Complexity Algorithms for Computing General Random Walk Graph Kernels on Sparse Graphscited by 3

50 most cited of 102 All 102 (JSON)