mlsanityData to 7 Oct 2026

MetaSDF: Meta-learning Signed Distance Functions

arXiv 2006.09662 ↗First posted 17 Jun 2020cs.CV cs.GR cs.LGcited by 214

Not on the map. Why?

Abstract (arXiv)

Neural implicit shape representations are an emerging paradigm that offers many potential benefits over conventional discrete representations, including memory efficiency at a high spatial resolution. Generalizing across shapes with such neural implicit representations amounts to learning priors over the respective function space and enables geometry reconstruction from partial or noisy observations. Existing generalization methods rely on conditioning a neural network on a low-dimensional latent code that is either regressed by an encoder or jointly optimized in the auto-decoder framework. Here, we formalize learning of a shape space as a meta-learning problem and leverage gradient-based meta-learning algorithms to solve this task. We demonstrate that this approach performs on par with auto-decoder based approaches while being an order of magnitude faster at test-time inference. We further demonstrate that the proposed gradient-based method outperforms encoder-decoder based methods that leverage pooling-based set encoders.

Key facts. Cited by 214 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 42; 2022: 46; 2023: 55; 2024: 31; 2025: 25; 2026: 15.

214 papers.

Sort:

By area:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  3. 2021Advances in Neural Renderingcited by 365
  4. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  5. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  6. 2021COIN: COmpression with Implicit Neural representationscited by 232
  7. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 204
  8. 2023EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingScited by 191
  9. 2022From data to functa: Your data point is a function and you can treat it like onecited by 183
  10. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  11. 2021Implicit Neural Representations for Image Compressioncited by 161
  12. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 142
38 more
  1. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  2. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 136
  3. 20213D Neural Scene Representations for Visuomotor Controlcited by 110
  4. 2021Neural Lumigraph Renderingcited by 105
  5. 2023Neural Kernel Surface Reconstructioncited by 102
  6. 2021A Structured Dictionary Perspective on Implicit Neural Representationscited by 100
  7. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  8. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  9. 2023ATT3D: Amortized Text-to-3D Object Synthesiscited by 87
  10. 2021LOLNeRF: Learn from One Lookcited by 84
  11. 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
  12. 2022COIN++: Neural Compression Across Modalitiescited by 81
  13. 2023Operator Learning with Neural Fields: Tackling PDEs on General Geometriescited by 80
  14. 2021FoV-NeRF: Foveated Neural Radiance Fields for Virtual Realitycited by 79
  15. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  16. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  17. 2022Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translationcited by 73
  18. 2022Unified Implicit Neural Stylizationcited by 67
  19. 2022ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 64
  20. 2023Deep Learning on Implicit Neural Representations of Shapescited by 62
  21. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  22. 2022Masked Wavelet Representation for Compact Neural Radiance Fieldscited by 57
  23. 2022CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representationscited by 56
  24. 2024SCube: Instant Large-Scale Scene Reconstruction using VoxSplatscited by 56
  25. 2022Parallel Inversion of Neural Radiance Fields for Robust Pose Estimationcited by 55
  26. 2021Generative Occupancy Fields for 3D Surface-Aware Image Synthesiscited by 51
  27. 2021Meta-Learning Sparse Implicit Neural Representationscited by 48
  28. 2021Learning Signal-Agnostic Manifolds of Neural Fieldscited by 45
  29. 2022A Level Set Theory for Neural Implicit Evolution under Explicit Flowscited by 42
  30. 2022Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priorscited by 42
  31. 2022Generalizable Implicit Neural Representations via Instance Pattern Composerscited by 38
  32. 2023Dynamic Point Fieldscited by 37
  33. 2023Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesiscited by 37
  34. 2021Meta-Auto-Decoder for Solving Parametric Partial Differential Equationscited by 36
  35. 2023NeMF: Inverse Volume Rendering with Neural Microflake Fieldcited by 34
  36. 2023VQ3D: Learning a 3D-Aware Generative Model on ImageNetcited by 32
  37. 2023DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Viewscited by 31
  38. 2023SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representationscited by 31

50 most cited of 214 All 214 (JSON)