mlsanityData to 7 Oct 2026

Local Implicit Grid Representations for 3D Scenes

arXiv 2003.08981 ↗First posted 19 Mar 2020cs.CV cs.CG cs.LGcited by 372

Not on the map. Why?

Abstract (arXiv)

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, complexity, or diversity. In this paper, we introduce Local Implicit Grid Representations, a new 3D shape representation designed for scalability and generality. The motivating idea is that most 3D surfaces share geometric details at some scale -- i.e., at a scale smaller than an entire object and larger than a small patch. We train an autoencoder to learn an embedding of local crops of 3D shapes at that size. Then, we use the decoder as a component in a shape optimization that solves for a set of latent codes on a regular grid of overlapping crops such that an interpolation of the decoded local shapes matches a partial or noisy observation. We demonstrate the value of this proposed approach for 3D surface reconstruction from sparse point observations, showing significantly better results than alternative approaches.

Key facts. Cited by 372 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 87; 2022: 100; 2023: 96; 2024: 59; 2025: 27; 2026: 3.

372 papers.

Sort:

By area:

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  3. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  4. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  5. 2021Neural Fields in Visual Computing and Beyondcited by 539
  6. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  7. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  8. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  9. 2021Advances in Neural Renderingcited by 365
  10. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  11. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  12. 20223D Neural Field Generation using Triplane Diffusioncited by 274
38 more
  1. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  2. 2021NeRV: Neural Representations for Videoscited by 255
  3. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  4. 2021Neural Articulated Radiance Fieldcited by 196
  5. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
  6. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  7. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  8. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  9. 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
  10. 2023HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusioncited by 152
  11. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 142
  12. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  13. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  14. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  15. 2021Local Texture Estimator for Implicit Representation Functioncited by 126
  16. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  17. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  18. 2023NeRF-DS: Neural Radiance Fields for Dynamic Specular Objectscited by 110
  19. 2021Light Field Neural Renderingcited by 108
  20. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 107
  21. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  22. 2021Neural Lumigraph Renderingcited by 105
  23. 2021imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Posecited by 102
  24. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  25. 2022Generative Neural Articulated Radiance Fieldscited by 101
  26. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 92
  27. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  28. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  29. 2021The Power of Points for Modeling Humans in Clothingcited by 90
  30. 2021Generative Models as Distributions of Functionscited by 89
  31. 2022ReLU Fields: The Little Non-linearity That Couldcited by 87
  32. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  33. 2022GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimationcited by 86
  34. 2021Pointly-Supervised Instance Segmentationcited by 83
  35. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  36. 2021DiGS : Divergence guided shape implicit neural representation for unoriented point cloudscited by 76
  37. 2021SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elementscited by 72
  38. 2022Neural Dual Contouringcited by 71

50 most cited of 372 All 372 (JSON)