mlsanityData to 7 Oct 2026

PointInfinity: Resolution-Invariant Point Diffusion Models

arXiv 2404.03566 ↗First posted 4 Apr 2024cs.CVcited by 15

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We present PointInfinity, an efficient family of point cloud diffusion models. Our core idea is to use a transformer-based architecture with a fixed-size, resolution-invariant latent representation. This enables efficient training with low-resolution point clouds, while allowing high-resolution point clouds to be generated during inference. More importantly, we show that scaling the test-time resolution beyond the training resolution improves the fidelity of generated point clouds and surfaces. We analyze this phenomenon and draw a link to classifier-free guidance commonly used in diffusion models, demonstrating that both allow trading off fidelity and variability during inference. Experiments on CO3D show that PointInfinity can efficiently generate high-resolution point clouds (up to 131k points, 31 times more than Point-E) with state-of-the-art quality.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 51 of its 61 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

51 of 61 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023GECCO: Geometrically-Conditioned Point Diffusion Models10 Mar
  2. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  3. 20223D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models1 Dec
  4. 20223D Neural Field Generation using Triplane Diffusion30 Nov
  5. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions24 Nov
  6. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  7. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  11. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  12. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
32 more
  1. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  2. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  3. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  4. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  5. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  6. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  7. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  8. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  9. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  10. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  11. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  12. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  13. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  14. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  15. 2020Learning Gradient Fields for Shape Generationcited by 245
  16. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  17. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  18. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 198
  19. 2022Scalable Adaptive Computation for Iterative Generationcited by 190
  20. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  21. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  22. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  23. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  24. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 129
  25. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  26. 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 97
  27. 2020Discrete Point Flow Networks for Efficient Point Cloud Generationcited by 87
  28. 2018Point Cloud GANcited by 79
  29. 2020Progressive Point Cloud Deconvolution Generation Networkcited by 46
  30. 2018SAGNet:Structure-aware Generative Network for 3D-Shape Modelingcited by 20
  31. 2023ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistencycited by 16
  32. 2020TM-NET: Deep Generative Networks for Textured Meshescited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 4; 2026: 5.

15 papers.

Sort:

By area:

  1. 2024SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglementcited by 65
  2. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Imagescited by 41
  3. 2025Anymate: A Dataset and Baselines for Learning 3D Object Riggingcited by 27
  4. 2024Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representationcited by 17
  5. 2025Not-So-Optimal Transport Flows for 3D Point Cloud Generationcited by 17
  6. 2024GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object Generationcited by 12
  7. 2025Textured 3D Regenerative Morphing with 3D Diffusion Priorcited by 6
  8. 2024Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Imagescited by 5
  9. 2024Diff-PCC: Diffusion-based Neural Compression for 3D Point Cloudscited by 2
  10. 2024Taming Feed-forward Reconstruction Models as Latent Encoders for 3D Generative Modelscited by 2
  11. 2026BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenizationcited by 2
  12. 2026Point-MF: Stabilizing One-Step Mean Flows for Single-Image Point Cloud Reconstructioncited by 0
3 more
  1. 2026PolycubeNet: A Dual-latent Diffusion Model for Polycube-Based Hexahedral Mesh Generationcited by 0
  2. 2026HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Imagecited by 0
  3. 2026PrintAnything: Learning an Intermediate Representation for 3D printing G-code Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
  2. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generation
  3. 2025Guided and Unguided Conditional Diffusion Mechanisms for Structured and Semantically-Aware 3D Point Cloud Generation
  4. 2024Point Cloud Resampling with Learnable Heat Diffusion
  5. 2023Point Cloud Pre-training with Diffusion Models
  6. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion
  7. 2026Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors
  8. 2025PDT: Point Distribution Transformation with Diffusion Models