mlsanityData to 7 Oct 2026

Multiresolution Deep Implicit Functions for 3D Shape Representation

arXiv 2109.05591 ↗First posted 12 Sep 2021cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

We introduce Multiresolution Deep Implicit Functions (MDIF), a hierarchical representation that can recover fine geometry detail, while being able to perform global operations such as shape completion. Our model represents a complex 3D shape with a hierarchy of latent grids, which can be decoded into different levels of detail and also achieve better accuracy. For shape completion, we propose latent grid dropout to simulate partial data in the latent space and therefore defer the completing functionality to the decoder side. This along with our multires design significantly improves the shape completion quality under decoder-only latent optimization. To the best of our knowledge, MDIF is the first deep implicit function model that can at the same time (1) represent different levels of detail and allow progressive decoding; (2) support both encoder-decoder inference and decoder-only latent optimization, and fulfill multiple applications; (3) perform detailed decoder-only shape completion. Experiments demonstrate its superior performance against prior art in various 3D reconstruction tasks.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 12 Sep 2021.

Builds on

26 of 41 references.

References · 26

  1. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2020Neural Sparse Voxel Fieldscited by 959
  8. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  9. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  10. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  11. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  12. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
14 more
  1. 2020State of the Art on Neural Renderingcited by 276
  2. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  3. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  4. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  5. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  6. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  7. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  8. 2020Curriculum DeepSDFcited by 62
  9. 2019Deep Level Sets: Implicit Surface Representations for 3D Shape Inferencecited by 52
  10. 2017O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysiscited by 47
  11. 2020Adversarial Generation of Continuous Implicit Shape Representationscited by 46
  12. 2017OctNetFusion: Learning Depth Fusion from Datacited by 45
  13. 2020Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completioncited by 33
  14. 2020Deep Implicit Volume Compressioncited by 26

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 14; 2023: 11; 2024: 5; 2025: 2.

35 papers.

Sort:

By area:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
  3. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 142
  4. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  5. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  6. 2023Grid-guided Neural Radiance Fields for Large Urban Scenescited by 99
  7. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 92
  8. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  9. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
  10. 2022Ponder: Point Cloud Pre-training via Neural Renderingcited by 50
  11. 2022Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Cloudscited by 42
  12. 2023Controllable Mesh Generation Through Sparse Latent Point Diffusion Modelscited by 40
23 more
  1. 2023Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulationcited by 27
  2. 2022PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categoriescited by 21
  3. 2022PINs: Progressive Implicit Networks for Multi-Scale Neural Representationscited by 19
  4. 2022PRIF: Primary Ray-based Implicit Functioncited by 17
  5. 2023T2TD: Text-3D Generation Model based on Prior Knowledge Guidancecited by 13
  6. 2022An Implicit Parametric Morphable Dental Modelcited by 12
  7. 2023RayDF: Neural Ray-surface Distance Fields with Multi-view Consistencycited by 12
  8. 2025ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Predictioncited by 11
  9. 2022PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformationcited by 7
  10. 2022OReX: Object Reconstruction from Planar Cross-sections Using Neural Fieldscited by 7
  11. 2024GridFormer: Point-Grid Transformer for Surface Reconstructioncited by 7
  12. 2025End-to-End Implicit Neural Representations for Classificationcited by 7
  13. 2024CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequencescited by 6
  14. 2022DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repaircited by 5
  15. 2024Towards Croppable Implicit Neural Representationscited by 5
  16. 2021UNIST: Unpaired Neural Implicit Shape Translation Networkcited by 4
  17. 2023Adaptive Local Basis Functions for Shape Completioncited by 4
  18. 2022Progressive Multi-scale Light Field Networkscited by 3
  19. 2024A Latent Implicit 3D Shape Model for Multiple Levels of Detailcited by 2
  20. 2023Continuous Levels of Detail for Light Field Networkscited by 1
  21. 2024AdaOcc: Adaptive-Resolution Occupancy Predictioncited by 1
  22. 2023Text2shape Deep Retrieval Model: Generating Initial Cases for Mechanical Part Redesign under the Context of Case-Based Reasoningcited by 0
  23. 2023Analysis of Sampling Strategies for Implicit 3D Reconstructioncited by 0