mlsanityData to 14 Oct 2026

Score-Based Point Cloud Denoising

arXiv 2107.10981 ↗First posted 23 Jul 2021cs.CVcited by 83

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Point clouds acquired from scanning devices are often perturbed by noise, which affects downstream tasks such as surface reconstruction and analysis. The distribution of a noisy point cloud can be viewed as the distribution of a set of noise-free samples p(x) convolved with some noise model n, leading to (p * n)(x) whose mode is the underlying clean surface. To denoise a noisy point cloud, we propose to increase the log-likelihood of each point from p * n via gradient ascent -- iteratively updating each point's position. Since p * n is unknown at test-time, and we only need the score (i.e., the gradient of the log-probability function) to perform gradient ascent, we propose a neural network architecture to estimate the score of p * n given only noisy point clouds as input. We derive objective functions for training the network and develop a denoising algorithm leveraging on the estimated scores. Experiments demonstrate that the proposed model outperforms state-of-the-art methods under a variety of noise models, and shows the potential to be applied in other tasks such as point cloud upsampling. The code is available at urlhttps://github.com/luost26/score-denoise.

Key facts. Cited by 83 papers in the map (data through 14 Oct 2026). Builds on 24 of its 38 references that are in the map. First posted on arXiv 23 Jul 2021.

Builds on

24 of 38 references.

References · 24

  1. 2016Densely Connected Convolutional Networkscited by 6,720
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  8. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  9. 2020Learning Gradient Fields for Shape Generationcited by 245
  10. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  11. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  12. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
12 more
  1. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  2. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  3. 2019Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaningcited by 58
  4. 2020Differentiable Manifold Reconstruction for Point Cloud Denoisingcited by 52
  5. 20183D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Modelcited by 47
  6. 2020Learning Graph-Convolutional Representations for Point Cloud Denoisingcited by 40
  7. 2019Feature Graph Learning for 3D Point Cloud Denoisingcited by 28
  8. 2020Graph Signal Processing for Geometric Data and Beyond: Theory and Applicationscited by 23
  9. 20193D Point Cloud Denoising via Deep Neural Network based Local Surface Estimationcited by 20
  10. 2020Dynamic Point Cloud Denoising via Manifold-to-Manifold Distancecited by 12
  11. 2015Graph-based denoising for time-varying point cloudscited by 11
  12. 2016Density-based Denoising of Point Cloudcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 16; 2023: 16; 2024: 22; 2025: 21; 2026: 5.

83 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  2. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 395
  3. 2022A Survey on Generative Diffusion Modelcited by 240
  4. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Modelscited by 103
  5. 2023Virtual Sparse Convolution for Multimodal 3D Object Detectioncited by 81
  6. 2022HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoisingcited by 73
  7. 2023Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --cited by 71
  8. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  9. 2024Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generationcited by 56
  10. 2024AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policiescited by 50
  11. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 48
  12. 2023Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functionscited by 43
38 more
  1. 2023An Ensemble Score Filter for Tracking High-Dimensional Nonlinear Dynamical Systemscited by 38
  2. 2023IterativePFN: True Iterative Point Cloud Filteringcited by 28
  3. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  4. 2021Deep Point Set Resampling via Gradient Fieldscited by 24
  5. 2023GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Graspingcited by 23
  6. 2025SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorizationcited by 21
  7. 2024SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flowcited by 20
  8. 2022PD-Flow: A Point Cloud Denoising Framework with Normalizing Flowscited by 19
  9. 2024P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoisingcited by 18
  10. 2021Deep Point Cloud Reconstructioncited by 15
  11. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  12. 2025MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstructioncited by 15
  13. 2023ChiroDiff: Modelling chirographic data with Diffusion Modelscited by 14
  14. 2022TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specificationcited by 13
  15. 2023Diffusion-Model-Assisted Supervised Learning of Generative Models for Density Estimationcited by 13
  16. 2022Contrastive Learning for Joint Normal Estimation and Point Cloud Filteringcited by 12
  17. 2023Score-PA: Score-based 3D Part Assemblycited by 12
  18. 2024Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generationcited by 12
  19. 2024Explore In-Context Segmentation via Latent Diffusion Modelscited by 12
  20. 2021PC2-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsamplingcited by 11
  21. 2022PCDNF: Revisiting Learning-based Point Cloud Denoising via Joint Normal Filteringcited by 11
  22. 2024StraightPCF: Straight Point Cloud Filteringcited by 10
  23. 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priorscited by 7
  24. 2022SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficultycited by 5
  25. 2022Neural Volumetric Mesh Generatorcited by 5
  26. 2024MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processingcited by 5
  27. 2025TFG-Flow: Training-free Guidance in Multimodal Generative Flowcited by 5
  28. 2025ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Groundingcited by 5
  29. 2022Point Cloud Denoising via Momentum Ascent in Gradient Fieldscited by 4
  30. 2022Dynamic Point Cloud Denoising via Gradient Fieldscited by 4
  31. 2023DiffuseGAE: Controllable and High-fidelity Image Manipulation from Disentangled Representationcited by 4
  32. 2024RayProNet: A Neural Point Field Framework for Radio Propagation Modeling in 3D Environmentscited by 4
  33. 2024Deep Learning for 3D Point Cloud Enhancement: A Surveycited by 4
  34. 2025Noise2Score3D: Tweedie's Approach for Unsupervised Point Cloud Denoisingcited by 4
  35. 2023Learning Gradient Fields for Scalable and Generalizable Irregular Packingcited by 3
  36. 20243D Object Detection from Point Cloud via Voting Step Diffusioncited by 3
  37. 2024Joint Point Cloud Upsampling and Cleaning with Octree-based CNNscited by 3
  38. 2025Robust 3D Object Detection using Probabilistic Point Clouds from Single-Photon LiDARscited by 3

50 most cited of 83 All 83 (JSON)