mlsanityData to 14 Oct 2026

BACON: Band-limited Coordinate Networks for Multiscale Scene Representation

arXiv 2112.04645 ↗First posted 9 Dec 2021cs.CV cs.GR cs.LGcited by 143

Not on the map. Why?

Abstract (arXiv)

Coordinate-based networks have emerged as a powerful tool for 3D representation and scene reconstruction. These networks are trained to map continuous input coordinates to the value of a signal at each point. Still, current architectures are black boxes: their spectral characteristics cannot be easily analyzed, and their behavior at unsupervised points is difficult to predict. Moreover, these networks are typically trained to represent a signal at a single scale, so naive downsampling or upsampling results in artifacts. We introduce band-limited coordinate networks (BACON), a network architecture with an analytical Fourier spectrum. BACON has constrained behavior at unsupervised points, can be designed based on the spectral characteristics of the represented signal, and can represent signals at multiple scales without per-scale supervision. We demonstrate BACON for multiscale neural representation of images, radiance fields, and 3D scenes using signed distance functions and show that it outperforms conventional single-scale coordinate networks in terms of interpretability and quality.

Key facts. Cited by 143 papers in the map (data through 14 Oct 2026). Builds on 62 of its 92 references that are in the map. First posted on arXiv 9 Dec 2021.

Builds on

62 of 92 references.

References · 62

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  9. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  10. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  11. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  12. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
38 more
  1. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  2. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  3. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  4. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  5. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  6. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  7. 2020Neural Sparse Voxel Fieldscited by 959
  8. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  9. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  10. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  11. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  12. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  13. 2020Convolutional Occupancy Networkscited by 761
  14. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  15. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  16. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  17. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  18. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  19. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  20. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  21. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  22. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
  23. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  24. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
  25. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  26. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
  27. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  28. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  29. 2021Advances in Neural Renderingcited by 365
  30. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  31. 2020State of the Art on Neural Renderingcited by 278
  32. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  33. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  34. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
  35. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  36. 2020Free View Synthesiscited by 231
  37. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  38. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 24; 2023: 36; 2024: 44; 2025: 22; 2026: 16.

143 papers.

Sort:

By area:

  1. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 274
  2. 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 229
  3. 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
  4. 2023Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fieldscited by 143
  5. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 138
  6. 2023StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Viewscited by 120
  7. 2023F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectoriescited by 118
  8. 2022Variable Bitrate Neural Fieldscited by 117
  9. 2023Operator Learning with Neural Fields: Tackling PDEs on General Geometriescited by 84
  10. 2022AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutionscited by 82
  11. 2023FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functionscited by 78
  12. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
38 more
  1. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  2. 2022NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modelingcited by 51
  3. 2023Watch Your Steps: Local Image and Scene Editing by Text Instructionscited by 50
  4. 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstructioncited by 50
  5. 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Setcited by 49
  6. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 47
  7. 2023CG3D: Compositional Generation for Text-to-3D via Gaussian Splattingcited by 42
  8. 2023Reference-guided Controllable Inpainting of Neural Radiance Fieldscited by 40
  9. 2022Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemblecited by 31
  10. 2023LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDARcited by 31
  11. 2023DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Viewscited by 31
  12. 2023Active Neural Mappingcited by 31
  13. 2022GenSDF: Two-Stage Learning of Generalizable Signed Distance Functionscited by 30
  14. 2022DINER: Disorder-Invariant Implicit Neural Representationcited by 30
  15. 2022Neural Fourier Filter Bankcited by 29
  16. 2023Disorder-invariant Implicit Neural Representationcited by 27
  17. 2023ResFields: Residual Neural Fields for Spatiotemporal Signalscited by 27
  18. 2022Residual Multiplicative Filter Networks for Multiscale Reconstructioncited by 25
  19. 2023Random-Access Neural Compression of Material Texturescited by 23
  20. 2023Polynomial Neural Fields for Subband Decomposition and Manipulationcited by 22
  21. 2023VisCo Grids: Surface Reconstruction with Viscosity and Coarea Gridscited by 20
  22. 2022PINs: Progressive Implicit Networks for Multi-Scale Neural Representationscited by 19
  23. 2023Compact Neural Graphics Primitives with Learned Hash Probingcited by 19
  24. 2024Tuning the Frequencies: Robust Training for Sinusoidal Neural Networkscited by 19
  25. 2022Neural Implicit Surface Evolutioncited by 18
  26. 20223D-Aware Video Generationcited by 17
  27. 2022PRIF: Primary Ray-based Implicit Functioncited by 17
  28. 2023Accelerating Neural Field Training via Soft Miningcited by 15
  29. 2024Nonparametric Teaching of Implicit Neural Representationscited by 15
  30. 2022Streamable Neural Fieldscited by 13
  31. 2023Regularize implicit neural representation by itselfcited by 13
  32. 2024PyGS: Large-scale Scene Representation with Pyramidal 3D Gaussian Splattingcited by 13
  33. 2024S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Videocited by 12
  34. 2024EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Renderingcited by 12
  35. 2022SinGRAF: Learning a 3D Generative Radiance Field for a Single Scenecited by 11
  36. 2024FINER++: Building a Family of Variable-periodic Functions for Activating Implicit Neural Representationcited by 11
  37. 2024Fast Training of Sinusoidal Neural Fields via Scaling Initializationcited by 11
  38. 2024MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Stepcited by 11

50 most cited of 143 All 143 (JSON)