mlsanityData to 7 Oct 2026

Fast Point Cloud Generation with Straight Flows

arXiv 2212.01747 ↗First posted 4 Dec 2022cs.CVcited by 56

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

Abstract (arXiv)

Diffusion models have emerged as a powerful tool for point cloud generation. A key component that drives the impressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While beneficial, the complexity of learning steps has limited its applications to many 3D real-world. To address this limitation, we propose Point Straight Flow (PSF), a model that exhibits impressive performance using one step. Our idea is based on the reformulation of the standard diffusion model, which optimizes the curvy learning trajectory into a straight path. Further, we develop a distillation strategy to shorten the straight path into one step without a performance loss, enabling applications to 3D real-world with latency constraints. We perform evaluations on multiple 3D tasks and find that our PSF performs comparably to the standard diffusion model, outperforming other efficient 3D point cloud generation methods. On real-world applications such as point cloud completion and training-free text-guided generation in a low-latency setup, PSF performs favorably.

Key facts. Cited by 56 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 44 of its 53 references that are in the map. First posted on arXiv 4 Dec 2022.

Builds on

44 of 53 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  2. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion7 Dec
  3. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 41

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Flow Matching for Generative Modelingcited by 5,426
  9. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  11. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  12. 2018Neural Ordinary Differential Equationscited by 3,733
29 more
  1. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  2. 2022Video Diffusion Modelscited by 2,280
  3. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  4. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  5. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  6. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  7. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  8. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  9. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speedcited by 344
  10. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  11. 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 332
  12. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 277
  13. 2020Learning Gradient Fields for Shape Generationcited by 245
  14. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  15. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  16. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  17. 2021Multimodal Virtual Point 3D Detectioncited by 166
  18. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  19. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  20. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Modelscited by 102
  21. 2019Theoretical guarantees for sampling and inference in generative models with latent diffusionscited by 97
  22. 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 97
  23. 2020Discrete Point Flow Networks for Efficient Point Cloud Generationcited by 87
  24. 2021SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Datacited by 78
  25. 2021FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimizationcited by 71
  26. 2018Learning to Reconstruct Shapes from Unseen Classescited by 60
  27. 2021Learning Skeletal Articulations with Neural Blend Shapescited by 52
  28. 2022Neural Volumetric Mesh Generatorcited by 5
  29. 2022How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversitycited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 16; 2025: 19; 2026: 13.

56 papers.

Sort:

By area:

  1. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  2. 2023Flow Matching in Latent Spacecited by 155
  3. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Modelcited by 84
  4. 2025Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modelingcited by 84
  5. 2024DepthFM: Fast Monocular Depth Estimation with Flow Matchingcited by 76
  6. 2025A Survey of World Models for Autonomous Drivingcited by 60
  7. 2024Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generationcited by 56
  8. 2024AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policiescited by 50
  9. 2023A Comprehensive Survey on Knowledge Distillation of Diffusion Modelscited by 45
  10. 2023Motion Flow Matching for Human Motion Synthesis and Editingcited by 36
  11. 2023Latent Space Editing in Transformer-Based Flow Matchingcited by 32
  12. 2025MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillationcited by 31
38 more
  1. 2024Wasserstein Flow Matching: Generative modeling over families of distributionscited by 27
  2. 2024Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformercited by 26
  3. 2024FlowTS: Time Series Generation via Rectified Flowcited by 22
  4. 2025GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Controlcited by 19
  5. 2024Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policiescited by 18
  6. 2025Not-So-Optimal Transport Flows for 3D Point Cloud Generationcited by 17
  7. 2024Compress3D: a Compressed Latent Space for 3D Generation from a Single Imagecited by 10
  8. 2024StraightPCF: Straight Point Cloud Filteringcited by 10
  9. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9
  10. 2023Guided Diffusion from Self-Supervised Diffusion Featurescited by 9
  11. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 9
  12. 2024EventFlow: Forecasting Temporal Point Processes with Flow Matchingcited by 8
  13. 2024Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Modelscited by 7
  14. 2025ARFlow: Human Action-Reaction Flow Matching with Physical Guidancecited by 7
  15. 2024MATCH POLICY: A Simple Pipeline from Point Cloud Registration to Manipulation Policiescited by 6
  16. 2025Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matchingcited by 6
  17. 2024Jigsaw++: Imagining Complete Shape Priors for Object Reassemblycited by 4
  18. 2025Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflowcited by 4
  19. 2025MFM-point: Multi-scale Flow Matching for Point Cloud Generationcited by 3
  20. 2024Point Cloud Synthesis Using Inner Product Transformscited by 2
  21. 2025SG-LDM: Semantic-Guided LiDAR Generation via Latent-Aligned Diffusioncited by 2
  22. 2025A Continuous-Time Consistency Model for 3D Point Cloud Generationcited by 2
  23. 2026Trajectory Consistency for One-Step Generation on Euler Mean Flowscited by 2
  24. 2026Generative Modeling with Orbit-Space Particle Flow Matchingcited by 2
  25. 2025AortaDiff: Volume-Guided Conditional Diffusion Models for Multi-Branch Aortic Surface Generationcited by 1
  26. 2025Hybrid Long and Short Range Flows for Point Cloud Filteringcited by 1
  27. 2025ArticFlow: Generative Simulation of Articulated Mechanismscited by 1
  28. 2026Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidancecited by 1
  29. 2023Patch-Wise Point Cloud Generation: A Divide-and-Conquer Approachcited by 0
  30. 2024Gen-Swarms: Adapting Deep Generative Models to Swarms of Dronescited by 0
  31. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 0
  32. 20253D Shape Generation: A Surveycited by 0
  33. 2025OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generationcited by 0
  34. 2025PUFM++: Point Cloud Upsampling via Enhanced Flow Matchingcited by 0
  35. 2026Class-Partitioned VQ-VAE and Latent Flow Matching for Point Cloud Scene Generationcited by 0
  36. 2026WeirNet: A Large-Scale 3D CFD Benchmark for Geometric Surrogate Modeling of Piano Key Weirscited by 0
  37. 2026CompoSE: Compositional Synthesis and Editing of 3D Shapes via Part-Aware Controlcited by 0
  38. 2026Rethinking 3D Shape Generation: Diffusion over Superquadricscited by 0

50 most cited of 56 All 56 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing Diffusion-based Point Cloud Generation with Smoothness Constraint
  2. 2025SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization
  3. 2024Point Cloud Resampling with Learnable Heat Diffusion
  4. 2025TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba
  5. 2026Point-MF: Stabilizing One-Step Mean Flows for Single-Image Point Cloud Reconstruction
  6. 2023Point Cloud Pre-training with Diffusion Models
  7. 2025InJecteD: Analyzing Trajectories and Drift Dynamics in Denoising Diffusion Probabilistic Models for 2D Point Cloud Generation
  8. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts