mlsanityData to 14 Oct 2026

PPSURF: Combining Patches and Point Convolutions for Detailed Surface Reconstruction

arXiv 2401.08518 ↗First posted 16 Jan 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage, and engineering. Current approaches either try to optimize a non-data-driven surface representation to fit the points, or learn a data-driven prior over the distribution of commonly occurring surfaces and how they correlate with potentially noisy point clouds. Data-driven methods enable robust handling of noise and typically either focus on a global or a local prior, which trade-off between robustness to noise on the global end and surface detail preservation on the local end. We propose PPSurf as a method that combines a global prior based on point convolutions and a local prior based on processing local point cloud patches. We show that this approach is robust to noise while recovering surface details more accurately than the current state-of-the-art. Our source code, pre-trained model and dataset are available at: https://github.com/cg-tuwien/ppsurf

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 16 Jan 2024.

Builds on

38 of 51 references.

References · 38

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  7. 2020Convolutional Occupancy Networkscited by 761
  8. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  9. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  10. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  11. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  12. 2020Local Implicit Grid Representations for 3D Scenescited by 373
26 more
  1. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  2. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  3. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  4. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  5. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 183
  6. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 147
  7. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  8. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  9. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  10. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  11. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 98
  12. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  13. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77
  14. 2022Neural Dual Contouringcited by 71
  15. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  16. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  17. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  18. 2020Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representationscited by 39
  19. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  20. 2022Iterative Poisson Surface Reconstruction (iPSR) for Unoriented Pointscited by 31
  21. 2021RetrievalFuse: Neural 3D Scene Reconstruction with a Databasecited by 28
  22. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  23. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  24. 2020Dynamic Plane Convolutional Occupancy Networkscited by 24
  25. 2021Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstructioncited by 13
  26. 2022Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Approximating Signed Distance Fields With Sparse Ellipsoidal Radial Basis Function Networks: A Dynamic Multi-Objective Optimization Strategycited by 0
  2. 2025NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervisioncited by 0
  3. 2026Recent Advances and Trends in Learning-based 3D Representationscited by 0