mlsanityData to 7 Oct 2026

GIFS: Neural Implicit Function for General Shape Representation

arXiv 2204.07126 ↗First posted 14 Apr 2022cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

Recent development of neural implicit function has shown tremendous success on high-quality 3D shape reconstruction. However, most works divide the space into inside and outside of the shape, which limits their representing power to single-layer and watertight shapes. This limitation leads to tedious data processing (converting non-watertight raw data to watertight) as well as the incapability of representing general object shapes in the real world. In this work, we propose a novel method to represent general shapes including non-watertight shapes and shapes with multi-layer surfaces. We introduce General Implicit Function for 3D Shape (GIFS), which models the relationships between every two points instead of the relationships between points and surfaces. Instead of dividing 3D space into predefined inside-outside regions, GIFS encodes whether two points are separated by any surface. Experiments on ShapeNet show that GIFS outperforms previous state-of-the-art methods in terms of reconstruction quality, rendering efficiency, and visual fidelity. Project page is available at https://jianglongye.com/gifs .

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 51 of its 70 references that are in the map. First posted on arXiv 14 Apr 2022.

Builds on

51 of 70 references.

References · 51

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  11. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
38 more
  1. 2017End-to-end Recovery of Human Shape and Posecited by 883
  2. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  3. 2020PCT: Point cloud transformercited by 730
  4. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  5. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  6. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  8. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  9. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  10. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  11. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  12. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  13. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  14. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  15. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  16. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  17. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  18. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  19. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  20. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  21. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  22. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 244
  23. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  24. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  25. 2017Learning a Multi-View Stereo Machinecited by 194
  26. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  27. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  28. 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
  29. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  30. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  31. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  32. 2016Unsupervised Learning of 3D Structure from Imagescited by 67
  33. 2020Curriculum DeepSDFcited by 62
  34. 2018Scan2Mesh: From Unstructured Range Scans to 3D Meshescited by 51
  35. 2020Adversarial Generation of Continuous Implicit Shape Representationscited by 46
  36. 2021Deep Implicit Surface Point Prediction Networkscited by 40
  37. 2021Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstructioncited by 36
  38. 2020Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Cloudscited by 30

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 19; 2024: 14; 2025: 7; 2026: 2.

45 papers.

Sort:

By area:

  1. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  2. 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
  3. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 46
  4. 2023NeUDF: Leaning Neural Unsigned Distance Fields with Volume Renderingcited by 40
  5. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  6. 2023Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessiancited by 34
  7. 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 32
  8. 2022GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representationcited by 28
  9. 2024UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusioncited by 23
  10. 2023Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Coveringcited by 21
  11. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  12. 2025GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splattingcited by 14
33 more
  1. 2023Mixing-Denoising Generalizable Occupancy Networkscited by 12
  2. 2023MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Drivingcited by 11
  3. 2024DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scalingcited by 9
  4. 2022NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representationcited by 7
  5. 2024Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstructioncited by 7
  6. 2024A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functionscited by 7
  7. 2023SuperUDF: Self-supervised UDF Estimation for Surface Reconstructioncited by 6
  8. 2024Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapescited by 6
  9. 2024DDM: A Metric for Comparing 3D Shapes Using Directional Distance Fieldscited by 5
  10. 2024CoFie: Learning Compact Neural Surface Representations with Coordinate Fieldscited by 5
  11. 2024Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Cloudscited by 5
  12. 2023A Review of Deep Learning-Powered Mesh Reconstruction Methodscited by 3
  13. 2023SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpaintingcited by 3
  14. 2025FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Modelscited by 3
  15. 2023FullFormer: Generating Shapes Inside Shapescited by 2
  16. 2023Learning to Predict Scene-Level Implicit 3D from Posed RGBD Datacited by 2
  17. 2023Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularizationcited by 2
  18. 2024Current Symmetry Group Equivariant Convolution Frameworks for Representation Learningcited by 2
  19. 2024ST-NeRP: Spatial-Temporal Neural Representation Learning with Prior Embedding for Patient-specific Imaging Studycited by 2
  20. 20243D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapescited by 2
  21. 2024Surface Reconstruction from Point Clouds via Grid-based Intersection Predictioncited by 1
  22. 2024Fast Medical Shape Reconstruction via Meta-learned Implicit Neural Representationscited by 1
  23. 2025Joint Neural SDF Reconstruction and Semantic Segmentation for CAD Modelscited by 1
  24. 2023Analysis of Sampling Strategies for Implicit 3D Reconstructioncited by 0
  25. 2023Contextualising Implicit Representations for Semantic Taskscited by 0
  26. 2023Polyhedral Surface: Self-supervised Point Cloud Reconstruction Based on Polyhedral Surfacecited by 0
  27. 2023IPVNet: Learning Implicit Point-Voxel Features for Open-Surface 3D Reconstructioncited by 0
  28. 2024DeepMIF: Deep Monotonic Implicit Fields for Large-Scale LiDAR 3D Mappingcited by 0
  29. 2025Neural Shortest Path for Surface Reconstruction from Point Cloudscited by 0
  30. 20253D Shape Generation: A Surveycited by 0
  31. 2025Performance and Efficiency of Climate In-Situ Data Reconstruction: Why Optimized IDW Outperforms kriging and Implicit Neural Representationcited by 0
  32. 2026SHARC: Reference point driven Spherical Harmonic Representation for Complex Shapescited by 0
  33. 2026Projective Normal Fields: A Convex Optimization Method for Constructing Smooth UDFscited by 0