mlsanityData to 14 Oct 2026

SAL: Sign Agnostic Learning of Shapes from Raw Data

arXiv 1911.10414 ↗First posted 23 Nov 2019cs.CV cs.GR cs.LGcited by 390

Not on the map. Why?

Abstract (arXiv)

Recently, neural networks have been used as implicit representations for surface reconstruction, modelling, learning, and generation. So far, training neural networks to be implicit representations of surfaces required training data sampled from a ground-truth signed implicit functions such as signed distance or occupancy functions, which are notoriously hard to compute. In this paper we introduce Sign Agnostic Learning (SAL), a deep learning approach for learning implicit shape representations directly from raw, unsigned geometric data, such as point clouds and triangle soups. We have tested SAL on the challenging problem of surface reconstruction from an un-oriented point cloud, as well as end-to-end human shape space learning directly from raw scans dataset, and achieved state of the art reconstructions compared to current approaches. We believe SAL opens the door to many geometric deep learning applications with real-world data, alleviating the usual painstaking, often manual pre-process.

Key facts. Cited by 390 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 78; 2022: 98; 2023: 104; 2024: 59; 2025: 38; 2026: 13.

390 papers.

Sort:

By area:

  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  2. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  3. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  4. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  5. 2021Neural Fields in Visual Computing and Beyondcited by 540
  6. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  7. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
  8. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  9. 2021Advances in Neural Renderingcited by 365
  10. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
  11. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  12. 20223D Neural Field Generation using Triplane Diffusioncited by 274
38 more
  1. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 231
  2. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  3. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  4. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 212
  5. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  6. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
  7. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 177
  8. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  9. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  10. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  11. 2021Improving neural implicit surfaces geometry with patch warpingcited by 137
  12. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  13. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  14. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 123
  15. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 109
  16. 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
  17. 2021Neural Lumigraph Renderingcited by 105
  18. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 103
  19. 2021imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Posecited by 103
  20. 2022Generative Neural Articulated Radiance Fieldscited by 101
  21. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  22. 2021Neural Scene Flow Priorcited by 91
  23. 2021Generative Models as Distributions of Functionscited by 89
  24. 2025Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modelingcited by 89
  25. 2024BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolationcited by 83
  26. 2021Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-Oncited by 81
  27. 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
  28. 2021FoV-NeRF: Foveated Neural Radiance Fields for Virtual Realitycited by 79
  29. 2021DiGS : Divergence guided shape implicit neural representation for unoriented point cloudscited by 77
  30. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 76
  31. 2022Object-Compositional Neural Implicit Surfacescited by 74
  32. 2022Neural Dual Contouringcited by 71
  33. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  34. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 70
  35. 2023EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videoscited by 69
  36. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  37. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  38. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67

50 most cited of 390 All 390 (JSON)