mlsanityData to 7 Oct 2026

Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model

arXiv 2311.12967 ↗First posted 21 Nov 2023cs.CV cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Feedforward generalizable models for implicit shape reconstruction from unoriented point cloud present multiple advantages, including high performance and inference speed. However, they still suffer from generalization issues, ranging from underfitting the input point cloud, to misrepresenting samples outside of the training data distribution, or with toplogies unseen at training. We propose here an efficient mechanism to remedy some of these limitations at test time. We combine the inter-shape data prior of the network with an intra-shape regularization prior of a Nystr"om Kernel Ridge Regression, that we further adapt by fitting its hyperprameters to the current shape. The resulting shape function defined in a shape specific Reproducing Kernel Hilbert Space benefits from desirable stability and efficiency properties and grants a shape adaptive expressiveness-robustness trade-off. We demonstrate the improvement obtained through our method with respect to baselines and the state-of-the-art using synthetic and real data.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 61 of its 82 references that are in the map. First posted on arXiv 21 Nov 2023.

Builds on

61 of 82 references.

References · 61

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  8. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  9. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  10. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  11. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  12. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
38 more
  1. 2020Convolutional Occupancy Networkscited by 760
  2. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  3. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  4. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  5. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  6. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  7. 2017Neural 3D Mesh Renderercited by 437
  8. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  9. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  10. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  11. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  12. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  13. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  14. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  15. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  16. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  17. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  18. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  19. 2019CvxNet: Learnable Convex Decompositioncited by 173
  20. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 146
  21. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  22. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  23. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  24. 2023Neural Kernel Surface Reconstructioncited by 102
  25. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  26. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  27. 2020Kernel methods through the roof: handling billions of points efficientlycited by 88
  28. 2022Learning Smooth Neural Functions via Lipschitz Regularizationcited by 86
  29. 2020PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representationscited by 81
  30. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  31. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  32. 2021DiGS : Divergence guided shape implicit neural representation for unoriented point cloudscited by 76
  33. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  34. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  35. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  36. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  37. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  38. 2020Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networkscited by 52

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 6; 2025: 4.

10 papers.

  1. 2024SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearizationcited by 19
  2. 2024Unsupervised Occupancy Learning from Sparse Point Cloudcited by 15
  3. 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priorscited by 7
  4. 2025SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splattingcited by 7
  5. 2025Sparfels: Fast Reconstruction from Sparse Unposed Imagerycited by 7
  6. 2025Anti-Aliased 2D Gaussian Splattingcited by 7
  7. 2024GeoTransfer : Generalizable Few-Shot Multi-View Reconstruction via Transfer Learningcited by 5
  8. 2024Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversariescited by 5
  9. 2024Toward Robust Neural Reconstruction from Sparse Point Setscited by 5
  10. 2025TextureSplat: Per-Primitive Texture Mapping for Reflective Gaussian Splattingcited by 3