mlsanityData to 7 Oct 2026

3D Shape Generation with Grid-based Implicit Functions

arXiv 2107.10607 ↗First posted 22 Jul 2021cs.CV cs.GR cs.LGcited by 48

Not on the map. Why?

Abstract (arXiv)

Previous approaches to generate shapes in a 3D setting train a GAN on the latent space of an autoencoder (AE). Even though this produces convincing results, it has two major shortcomings. As the GAN is limited to reproduce the dataset the AE was trained on, we cannot reuse a trained AE for novel data. Furthermore, it is difficult to add spatial supervision into the generation process, as the AE only gives us a global representation. To remedy these issues, we propose to train the GAN on grids (i.e. each cell covers a part of a shape). In this representation each cell is equipped with a latent vector provided by an AE. This localized representation enables more expressiveness (since the cell-based latent vectors can be combined in novel ways) as well as spatial control of the generation process (e.g. via bounding boxes). Our method outperforms the current state of the art on all established evaluation measures, proposed for quantitatively evaluating the generative capabilities of GANs. We show limitations of these measures and propose the adaptation of a robust criterion from statistical analysis as an alternative.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 29 of its 35 references that are in the map. First posted on arXiv 22 Jul 2021.

Builds on

29 of 35 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  8. 2017Improved Training of Wasserstein GANscited by 2,223
  9. 2014Conditional Generative Adversarial Netscited by 2,152
  10. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  12. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
17 more
  1. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  2. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  3. 2018Which Training Methods for GANs do actually Converge?cited by 672
  4. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  5. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  6. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  7. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  8. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  9. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  10. 2017Stabilizing Training of Generative Adversarial Networks through Regularizationcited by 118
  11. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  12. 2018Point Cloud GANcited by 79
  13. 2020Adversarial Generation of Continuous Implicit Shape Representationscited by 46
  14. 2017SurfNet: Generating 3D shape surfaces using deep residual networkscited by 32
  15. 2013A new graph-based two-sample test for multivariate and object datacited by 24
  16. 2019A Convolutional Decoder for Point Clouds using Adaptive Instance Normalizationcited by 8
  17. 2019Gradient penalty from a maximum margin perspectivecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 19; 2024: 10; 2025: 4; 2026: 2.

48 papers.

Sort:

By area:

  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  2. 2021Neural Fields in Visual Computing and Beyondcited by 539
  3. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  4. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  5. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  6. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 129
  7. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  8. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100
  9. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  10. 2023TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Modelscited by 86
  11. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  12. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
36 more
  1. 2022ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 64
  2. 2022CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Languagecited by 46
  3. 2021Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequencescited by 38
  4. 2024An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusioncited by 34
  5. 2023Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulationcited by 27
  6. 2023Multi-modal Machine Learning in Engineering Design: A Review and Future Directionscited by 27
  7. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  8. 2024Make-A-Shape: a Ten-Million-scale 3D Shape Modelcited by 25
  9. 2023EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervisioncited by 18
  10. 2025LL3M: Large Language 3D Modelerscited by 18
  11. 2023Pushing the Limits of 3D Shape Generation at Scalecited by 11
  12. 2023MinD-3D: Reconstruct High-quality 3D objects in Human Braincited by 11
  13. 2023Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflectioncited by 10
  14. 2023ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 10
  15. 2024CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimizationcited by 8
  16. 2024A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Partscited by 8
  17. 2024Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalabilitycited by 7
  18. 2024MinD-3D++: Advancing fMRI-Based 3D Reconstruction with High-Quality Textured Mesh Generation and a Comprehensive Datasetcited by 6
  19. 2025Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Modelscited by 6
  20. 2021HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulationcited by 5
  21. 2022ImpDet: Exploring Implicit Fields for 3D Object Detectioncited by 4
  22. 2023Neural Implicit Shape Editing using Boundary Sensitivitycited by 4
  23. 2023Learning Versatile 3D Shape Generation with Improved AR Modelscited by 3
  24. 2023Text-guided Image-and-Shape Editing and Generation: A Short Surveycited by 3
  25. 2024Occupancy-Based Dual Contouringcited by 3
  26. 2024GenUDC: High Quality 3D Mesh Generation with Unsigned Dual Contouring Representationcited by 3
  27. 2023Diverse Shape Completion via Style Modulated Generative Adversarial Networkscited by 2
  28. 2022Deep Generative Models on 3D Representations: A Surveycited by 1
  29. 20233D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capabilitycited by 1
  30. 2025Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Imagecited by 1
  31. 20263D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesiscited by 1
  32. 2023Analysis of Sampling Strategies for Implicit 3D Reconstructioncited by 0
  33. 2023Towards AI-Architecture Liberty: A Comprehensive Survey on Design and Generation of Virtual Architecture by Deep Learningcited by 0
  34. 2024Masked Generative Extractor for Synergistic Representation and 3D Generation of Point Cloudscited by 0
  35. 20253D Shape Generation: A Surveycited by 0
  36. 2026CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representationcited by 0