mlsanityData to 7 Oct 2026

3DILG: Irregular Latent Grids for 3D Generative Modeling

arXiv 2205.13914 ↗First posted 27 May 2022cs.CVcited by 92

Not on the map. Why?

Cited by 23 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a new representation for encoding 3D shapes as neural fields. The representation is designed to be compatible with the transformer architecture and to benefit both shape reconstruction and shape generation. Existing works on neural fields are grid-based representations with latents defined on a regular grid. In contrast, we define latents on irregular grids, enabling our representation to be sparse and adaptive. In the context of shape reconstruction from point clouds, our shape representation built on irregular grids improves upon grid-based methods in terms of reconstruction accuracy. For shape generation, our representation promotes high-quality shape generation using auto-regressive probabilistic models. We show different applications that improve over the current state of the art. First, we show results for probabilistic shape reconstruction from a single higher resolution image. Second, we train a probabilistic model conditioned on very low resolution images. Third, we apply our model to category-conditioned generation. All probabilistic experiments confirm that we are able to generate detailed and high quality shapes to yield the new state of the art in generative 3D shape modeling.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). Builds on 58 of its 72 references that are in the map. First posted on arXiv 27 May 2022.

Builds on

58 of 72 references.

References · 58

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017Neural Discrete Representation Learningcited by 4,650
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2013Auto-Encoding Variational Bayescited by 3,980
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  9. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  11. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  12. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
38 more
  1. 2015Variational Inference with Normalizing Flowscited by 2,161
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  3. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  4. 2020Point Transformercited by 1,462
  5. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  6. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  7. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  8. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  9. 2016Pixel Recurrent Neural Networkscited by 814
  10. 2020Convolutional Occupancy Networkscited by 760
  11. 2020PCT: Point cloud transformercited by 730
  12. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  13. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  14. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  15. 2021Neural Fields in Visual Computing and Beyondcited by 539
  16. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  17. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  18. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  19. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  20. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  21. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  22. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  23. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  24. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  25. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  26. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  27. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  28. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  29. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  30. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 195
  31. 2016A Theory of Generative ConvNetcited by 174
  32. 2019CvxNet: Learnable Convex Decompositioncited by 173
  33. 2020SceneFormer: Indoor Scene Generation with Transformerscited by 154
  34. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  35. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  36. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  37. 2020Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classificationcited by 57
  38. 2018Learning Descriptor Networks for 3D Shape Synthesis and Analysiscited by 56

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 26; 2024: 32; 2025: 16; 2026: 12.

92 papers.

Sort:

By area:

  1. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  2. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  3. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generationcited by 181
  4. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Priorcited by 157
  5. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 129
  6. 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refinercited by 120
  7. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  8. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
  9. 2023Generative AI meets 3D: A Survey on Text-to-3D in AIGC Eracited by 61
  10. 2023Mosaic-SDF for 3D Generative Modelscited by 48
  11. 2024OctFusion: Octree-based Diffusion Models for 3D Shape Generationcited by 40
  12. 2024An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusioncited by 34
38 more
  1. 2024Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Trackingcited by 27
  2. 2025OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generationcited by 27
  3. 2022Neural Shape Deformation Priorscited by 26
  4. 2024Make-A-Shape: a Ten-Million-scale 3D Shape Modelcited by 25
  5. 2024MVD2: Efficient Multiview 3D Reconstruction for Multiview Diffusioncited by 22
  6. 2022ALTO: Alternating Latent Topologies for Implicit 3D Reconstructioncited by 21
  7. 2023CAD: Photorealistic 3D Generation via Adversarial Distillationcited by 18
  8. 2024AToM: Amortized Text-to-Mesh using 2D Diffusioncited by 18
  9. 2025Nautilus: Locality-aware Autoencoder for Scalable Mesh Generationcited by 18
  10. 2023CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embeddingcited by 16
  11. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  12. 2023EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generationcited by 16
  13. 2024LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusioncited by 16
  14. 2024TAR3D: Creating High-Quality 3D Assets via Next-Part Predictioncited by 16
  15. 2024Atlas Gaussians Diffusion for 3D Generationcited by 15
  16. 2023Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generationcited by 14
  17. 2023Functional Diffusioncited by 13
  18. 2024Topology-Aware Latent Diffusion for 3D Shape Generationcited by 13
  19. 2024NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generationcited by 13
  20. 2023RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generationcited by 12
  21. 2024GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesiscited by 12
  22. 2023Pushing the Limits of 3D Shape Generation at Scalecited by 11
  23. 2024Compress3D: a Compressed Latent Space for 3D Generation from a Single Imagecited by 10
  24. 2024Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodingscited by 10
  25. 20243D Shape Tokenization via Latent Flow Matchingcited by 10
  26. 2023CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Explorationcited by 9
  27. 2023SENS: Part-Aware Sketch-based Implicit Neural Shape Modelingcited by 8
  28. 2024GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulationcited by 8
  29. 2024A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Partscited by 8
  30. 2024Coherent 3D Scene Diffusion From a Single RGB Imagecited by 8
  31. 2025PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimizationcited by 8
  32. 2024Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalabilitycited by 7
  33. 2024DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Modelcited by 7
  34. 2024Multi-scale Latent Point Consistency Models for 3D Shape Generationcited by 6
  35. 2025Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Modelscited by 6
  36. 2025TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimizationcited by 6
  37. 2024SweepNet: Unsupervised Learning Shape Abstraction via Neural Sweeperscited by 5
  38. 2025Functional Mean Flow in Hilbert Spacecited by 5

50 most cited of 92 All 92 (JSON)