mlsanityData to 14 Oct 2026

Learning Positional Embeddings for Coordinate-MLPs

arXiv 2112.11577 ↗First posted 21 Dec 2021cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose a novel method to enhance the performance of coordinate-MLPs by learning instance-specific positional embeddings. End-to-end optimization of positional embedding parameters along with network weights leads to poor generalization performance. Instead, we develop a generic framework to learn the positional embedding based on the classic graph-Laplacian regularization, which can implicitly balance the trade-off between memorization and generalization. This framework is then used to propose a novel positional embedding scheme, where the hyperparameters are learned per coordinate (i.e, instance) to deliver optimal performance. We show that the proposed embedding achieves better performance with higher stability compared to the well-established random Fourier features (RFF). Further, we demonstrate that the proposed embedding scheme yields stable gradients, enabling seamless integration into deep architectures as intermediate layers.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

38 of 48 references.

References · 38

  1. 2018Neural Ordinary Differential Equationscited by 3,779
  2. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  7. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  8. 2018On the Spectral Bias of Neural Networkscited by 1,341
  9. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  10. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  11. 2018Self-Attention with Relative Position Representationscited by 1,120
  12. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
26 more
  1. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  2. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  3. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  4. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  5. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  6. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  7. 2018Universal Transformerscited by 647
  8. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  9. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  10. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  11. 2021COIN: COmpression with Implicit Neural representationscited by 233
  12. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  13. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  14. 2020DeRF: Decomposed Radiance Fieldscited by 163
  15. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  16. 2019NASA: Neural Articulated Shape Approximationcited by 149
  17. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 114
  18. 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102
  19. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  20. 2020Object-Centric Neural Scene Renderingcited by 90
  21. 2020Learning to Encode Position for Transformer with Continuous Dynamical Modelcited by 61
  22. 2019Reconstructing continuous distributions of 3D protein structure from cryo-EM imagescited by 56
  23. 2019Learning a Neural 3D Texture Space from 2D Exemplarscited by 53
  24. 2019Encoding word order in complex embeddingscited by 53
  25. 2021Rethinking Positional Encodingcited by 37
  26. 2021LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representationcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 6.

7 papers.

  1. 2024A Sampling Theory Perspective on Activations for Implicit Neural Representationscited by 24
  2. 2022Intrinsic Neural Fields: Learning Functions on Manifoldscited by 20
  3. 2024HR-INR: Continuous Space-Time Video Super-Resolution via Event Cameracited by 6
  4. 2024RBF-PINN: Non-Fourier Positional Embedding in Physics-Informed Neural Networkscited by 5
  5. 2024A Simple and Generalist Approach for Panoptic Segmentationcited by 3
  6. 2024Feature Mapping in Physics-Informed Neural Networks (PINNs)cited by 2
  7. 2024On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encodingcited by 0