mlsanityData to 7 Oct 2026

ShapeFormer: Transformer-based Shape Completion via Sparse Representation

arXiv 2201.10326 ↗First posted 25 Jan 2022cs.CV cs.GR cs.LGcited by 106

Not on the map. Why?

Abstract (arXiv)

We present ShapeFormer, a transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds. The resultant distribution can then be sampled to generate likely completions, each exhibiting plausible shape details while being faithful to the input. To facilitate the use of transformers for 3D, we introduce a compact 3D representation, vector quantized deep implicit function, that utilizes spatial sparsity to represent a close approximation of a 3D shape by a short sequence of discrete variables. Experiments demonstrate that ShapeFormer outperforms prior art for shape completion from ambiguous partial inputs in terms of both completion quality and diversity. We also show that our approach effectively handles a variety of shape types, incomplete patterns, and real-world scans.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). Builds on 59 of its 79 references that are in the map. First posted on arXiv 25 Jan 2022.

Builds on

59 of 79 references.

References · 59

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017Neural Discrete Representation Learningcited by 4,650
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  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. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
38 more
  1. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  2. 2020Rethinking Attention with Performerscited by 1,584
  3. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  4. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  7. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  8. 2016Pixel Recurrent Neural Networkscited by 814
  9. 2018Image Transformercited by 770
  10. 2020Convolutional Occupancy Networkscited by 760
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  12. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  13. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  14. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  15. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  16. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  17. 2018PCN: Point Completion Networkcited by 382
  18. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  19. 2019Axial Attention in Multidimensional Transformerscited by 350
  20. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  21. 2018Generating Wikipedia by Summarizing Long Sequencescited by 333
  22. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  23. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  24. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  25. 2021Generating Images with Sparse Representationscited by 262
  26. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  27. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  28. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  29. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
  30. 2020SceneFormer: Indoor Scene Generation with Transformerscited by 154
  31. 2017PixelSNAIL: An Improved Autoregressive Generative Modelcited by 137
  32. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  33. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  34. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  35. 2016Neural Autoregressive Distribution Estimationcited by 94
  36. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  37. 2019Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Eracited by 87
  38. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 19; 2023: 36; 2024: 20; 2025: 25; 2026: 6.

106 papers.

Sort:

By area:

  1. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  2. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  3. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  4. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  5. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  6. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Priorcited by 157
  7. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functionscited by 133
  8. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  9. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 129
  10. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 120
  11. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 92
  12. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
38 more
  1. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
  2. 2022ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Modelcited by 62
  3. 2024Advances in 3D Generation: A Surveycited by 62
  4. 2022CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Languagecited by 46
  5. 2022Surface Reconstruction from Point Clouds: A Survey and a Benchmarkcited by 41
  6. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 41
  7. 2022Autoregressive 3D Shape Generation via Canonical Mappingcited by 37
  8. 2023Point-Cloud Completion with Pretrained Text-to-image Diffusion Modelscited by 37
  9. 2023DiffComplete: Diffusion-based Generative 3D Shape Completioncited by 35
  10. 2024An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusioncited by 34
  11. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  12. 2023MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Visioncited by 31
  13. 2023Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulationcited by 27
  14. 20233DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Processcited by 25
  15. 2023GINA-3D: Learning to Generate Implicit Neural Assets in the Wildcited by 25
  16. 2024Make-A-Shape: a Ten-Million-scale 3D Shape Modelcited by 25
  17. 2024SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generationcited by 24
  18. 2022PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categoriescited by 21
  19. 20223D Vision with Transformers: A Surveycited by 21
  20. 2024NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fieldscited by 20
  21. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  22. 2024LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusioncited by 16
  23. 2024Atlas Gaussians Diffusion for 3D Generationcited by 15
  24. 2023Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generationcited by 14
  25. 2023Functional Diffusioncited by 13
  26. 2023Slice3D: Multi-Slice, Occlusion-Revealing, Single View 3D Reconstructioncited by 13
  27. 2025ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Graspingcited by 13
  28. 20233D VR Sketch Guided 3D Shape Prototyping and Explorationcited by 12
  29. 2023RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generationcited by 12
  30. 2024SC-Diff: 3D Shape Completion with Latent Diffusion Modelscited by 10
  31. 2024Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodingscited by 10
  32. 2025GenPC: Zero-shot Point Cloud Completion via 3D Generative Priorscited by 9
  33. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 9
  34. 2023SCARP: 3D Shape Completion in ARbitrary Poses for Improved Graspingcited by 8
  35. 2024A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Partscited by 8
  36. 2025PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimizationcited by 8
  37. 2022NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representationcited by 7
  38. 2023NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDFcited by 7

50 most cited of 106 All 106 (JSON)