mlsanityData to 7 Oct 2026

AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation

arXiv 2203.09516 ↗First posted 17 Mar 2022cs.CV cs.LGcited by 208

Not on the map. Why?

Cited by 51 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Powerful priors allow us to perform inference with insufficient information. In this paper, we propose an autoregressive prior for 3D shapes to solve multimodal 3D tasks such as shape completion, reconstruction, and generation. We model the distribution over 3D shapes as a non-sequential autoregressive distribution over a discretized, low-dimensional, symbolic grid-like latent representation of 3D shapes. This enables us to represent distributions over 3D shapes conditioned on information from an arbitrary set of spatially anchored query locations and thus perform shape completion in such arbitrary settings (e.g., generating a complete chair given only a view of the back leg). We also show that the learned autoregressive prior can be leveraged for conditional tasks such as single-view reconstruction and language-based generation. This is achieved by learning task-specific naive conditionals which can be approximated by light-weight models trained on minimal paired data. We validate the effectiveness of the proposed method using both quantitative and qualitative evaluation and show that the proposed method outperforms the specialized state-of-the-art methods trained for individual tasks. The project page with code and video visualizations can be found at https://yccyenchicheng.github.io/AutoSDF/.

Key facts. Cited by 208 papers in the map (data through 7 Oct 2026). Builds on 45 of its 51 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

45 of 51 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2017Neural Discrete Representation Learningcited by 4,650
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  9. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  10. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  11. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
33 more
  1. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  2. 2016Pixel Recurrent Neural Networkscited by 814
  3. 2018Image Transformercited by 770
  4. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  5. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  6. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  7. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  8. 2018PCN: Point Completion Networkcited by 382
  9. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  10. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  11. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  12. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  13. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  14. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  15. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  16. 2018Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddingscited by 169
  17. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  18. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  19. 2017PixelSNAIL: An Improved Autoregressive Generative Modelcited by 137
  20. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  21. 2016Video Pixel Networkscited by 108
  22. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  23. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  24. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  25. 2018Learning Shape Priors for Single-View 3D Completion and Reconstructioncited by 68
  26. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  27. 2013RNADE: The real-valued neural autoregressive density-estimatorcited by 65
  28. 2020Multimodal Shape Completion via Conditional Generative Adversarial Networkscited by 61
  29. 20193DN: 3D Deformation Networkcited by 60
  30. 2019ShapeGlot: Learning Language for Shape Differentiationcited by 54
  31. 20183D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Imagecited by 40
  32. 2021Deep Implicit Surface Point Prediction Networkscited by 40
  33. 2021PixelTransformer: Sample Conditioned Signal Generationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 23; 2023: 64; 2024: 68; 2025: 29; 2026: 24.

208 papers.

Sort:

By area:

  1. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  2. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  3. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  4. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  5. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  6. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  7. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  8. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  9. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  10. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  11. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  12. 2023Scalable 3D Captioning with Pretrained Modelscited by 201
38 more
  1. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generationcited by 181
  2. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Priorcited by 157
  3. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functionscited by 133
  4. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 129
  5. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  6. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  7. 2023HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidancecited by 109
  8. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  9. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100
  10. 2024MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstructioncited by 94
  11. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 92
  12. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  13. 2023AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homescited by 81
  14. 2023Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFscited by 76
  15. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  16. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  17. 20223D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Modelscited by 67
  18. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
  19. 2022ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Modelcited by 62
  20. 2024Advances in 3D Generation: A Surveycited by 62
  21. 2025HoloPart: Generative 3D Part Amodal Segmentationcited by 57
  22. 2023One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Eracited by 55
  23. 2023Online Clustered Codebookcited by 55
  24. 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysiscited by 52
  25. 2025RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assetscited by 47
  26. 2022CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Languagecited by 46
  27. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 45
  28. 2023Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Modelscited by 43
  29. 2023SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priorscited by 43
  30. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  31. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Imagescited by 41
  32. 2023Controllable Mesh Generation Through Sparse Latent Point Diffusion Modelscited by 40
  33. 2024OctFusion: Octree-based Diffusion Models for 3D Shape Generationcited by 40
  34. 2023ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Modelcited by 38
  35. 2024SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAEcited by 38
  36. 2022Autoregressive 3D Shape Generation via Canonical Mappingcited by 37
  37. 2023Point-Cloud Completion with Pretrained Text-to-image Diffusion Modelscited by 37
  38. 2023DiffComplete: Diffusion-based Generative 3D Shape Completioncited by 35

50 most cited of 208 All 208 (JSON)