Overview

A curated list of awesome 3D point cloud denoising (and closely related fields) papers.

This is a work in continuous progress.

For any suggestions, please contact garnungalejandro@gmail.com.

Thank you and enjoy the 3D point cloud denoising world.

Updated: 13/01/2025

Keywords

trad.: traditional filter | var.: variational-based | pde: PDE-based | spec.: spectral-based | dl.: deep learning | un.: unsupervised | rec.: resampling/compression | sur.: surface reconstruction | ne.: normal estimation | inp.: inpainting | res.: super-resolution | mesh.: mesh denoising | surv.: survey | oth.: other

Gradations

• ◼️ Less than 5 citations
• 🔹 Less than 25 citations
• 🔸 Between 25 and 50 citations
• 🔥 More than 50 citations
• 🌟 More than 150 citations

Table of Contents

2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024, 2025

2003

• [Link] Mesh-Independent Surface Interpolation MLS [][oth.] 🌟
• [Link] Non-Iterative, Feature-Preserving Mesh Smoothing [code] 🌟
• [Link] Bilateral mesh denoising [code] 🔥

2004

...

2005

...

2006

• [Link] Point cloud denoising using robust principal component analysis [][] 🔸

2007

• [Link] Fast and Effective Feature-Preserving Mesh Denoising [code] 🌟

2008

• [Link] Nonlocal discrete regularization on weighted graphs: A framework for image and manifold processing [][] 🌟

2009

• [Link] Noise reduction and modeling methods of TLS point cloud based on R-tree [][] 🔹
• [Link] Algorithm for 3D Point Cloud Denoising [][] 🔹
• [Link] 3D Body Point Cloud Data Denoising and Registration [][] ◼️

2010

• [Link] Scatter Point Cloud Denoising Based on Self-Adaptive Optimal Neighborhood [][] 🔹
• [Link] ℓ1-Sparse reconstruction of sharp point set surfaces 🌟

2011

• [Link] Nonlocal PDEs-Based Morphology on Weighted Graphs for Image and Data Processing [][] 🔥
• [Link] Bilateral Normal Filtering for Mesh Denoising [code] 🌟

2012

• [Link] Denoising point cloud [][] 🔹
• [Link] A New near Point Denoising Algorithm for Point Cloud [][] ◼️

2013

• [Link] Motion estimation and filtered prediction for dynamic point cloud attribute compression [][] ◼️
• [Link] Mesh Denoising via L0 Minimization [code1][code2][code3] 🌟

2014

• [Link] A General Framework for Bilateral and Mean Shift Filtering [][] 🔸
• [Link] Research on 3D scanning point cloud de-nosing [][] 🔹

2015

• [Link] Denoising Point Sets via L0 Minimization [][] 🌟
• [Link] 3D point cloud denoising and normal estimation for 3D surface reconstruction [][] 🔹
• [Link] Guided Mesh Normal Filtering [code] 🌟
• [Link] Adaptive Denoising Algorithm for Scanning Beam Points Based on Angle Thresholds [][] ◼️
• [Link] Graph-based denoising for time varying point clouds [][] 🔥

2016

• [Link] Density-based Denoising of Point Cloud [][] 🔸
• [Link] Mesh Denoising via Cascaded Normal Regression [][] mesh.
• [Link] Point Cloud Noise and Outlier Removal for Image-Based 3D Reconstruction [][] 🔥
• [Link] Robust Feature-Preserving Denoising of 3D Point Clouds [][] 🔹

2017

• [Link] Point Cloud Denoising via Moving RPCA [][] 🔥
• [Link] The bilateral filter for point clouds [code] 🔥
• [Link] Guided 3D point cloud filtering [code][] 🔸
• [Link] Data-Driven Sparse Priors of 3D Shapes [][] 🔹
• [Link] Guided point cloud denoising via sharp feature skeletons 🔸

2018

• [Link] Fast 3D Point Cloud Denoising via Bipartite Graph Approximation & Total Variation 🔹
• [Link] Weighted Multi-projection: 3D Point Cloud Denoising with Estimated Tangent Planes 🔹
• [Link] EC-Net: an Edge-aware Point set Consolidation Network [code] 🌟
• [Link] Pointpronets: Consolidation of point clouds with convolutional neural networks [][] 🔥
• [Link] Static/Dynamic Filtering for Mesh Geometry [code] 🔥
• [Link] Robust and effective mesh denoising using L0 sparse regularization [][] 🔸
• [Link] Constraint based point set denoising using normal voting tensor and restricted quadratic error metrics [][] 🔸
• [Link] 3D Point Cloud Denoising via Bipartite Graph Approximation and Reweighted Graph Laplacian 🔹
• [Link] 3D Shape Processing by Convolutional Denoising Autoencoders on Local Patches 🔸
• [Link] DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense [code] 🔥

2019

• [Link] A 3D point cloud filtering method for leaves based on manifold distance and normal estimation [][] 🔸
• [Link] 3D Point Cloud Denoising via Deep Neural Network based Local Surface Estimation 🔥
• [Link] 3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model [code] 🔥
• [Link] PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds [code] 🌟
• [Link] A Novel Denoising Algorithm for Airborne Lidar Point Cloud Based on Empirical Mode Decomposition [][] ◼️
• [Link] A 3D Point Cloud Filtering Algorithm based on Surface Variation Factor Classification [][] 🔹
• [Link] Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering [code] 🔥
• [Link] Differentiable Surface Splatting for Point-based Geometry Processing [code] 🌟
• [Link] Low Rank Matrix Approximation for 3D Geometry Filtering [][] 🔥
• [Link] Method for Filtering Dense Noise from Laser Scanning Data [][] ◼️
• [Link] A novel anisotropic second order regularization for mesh denoising [][] 🔹
• [Link] Denoising of 3D Point clouds [][] ◼️
• [Link] Total denoising: Unsupervised learning of 3D point cloud cleaning [code] 🔥
• [Link] 3D Point Cloud Color Denoising Using Convex Graph-Signal Smoothness Priors [][] 🔹

2020

• [Link] Feature Graph Learning for 3D Point Cloud Denoising [][] 🔥
• [Link] Point Cloud Denoising via Feature Graph Laplacian Regularization [][] 🔥
• [Link] Pointfilter: Point Cloud Filtering via Encoder Decoder Modeling [code] 🔥
• [Link] Non-Local Part-Aware Point Cloud Denoising [][] 🔹
• [Link] Research on denoising algorithm of 3D point cloud data based on curvature change [][] ◼️
• [Link] Point Cloud Denoising Algorithm Based on Noise Classification [][] 🔹
• [Link] Learning robust graph-convolutional representations for point cloud denoising 🔸
• [Link] 3D point cloud registration denoising method for human motion image using deep learning algorithm 🔹
• [Link] CNN-based Lidar Point Cloud De-Noising in Adverse Weather [code][] 🔥
• [Link] A feature-preserving framework for point cloud denoising [][] 🔹
• [Link] Sparse Regularization-Based Approach for Point Cloud Denoising and Sharp Features Enhancement [][] 🔹
• [Link] Deep feature-preserving normal estimation for point cloud filtering [][] 🔥
• [Link] Deep Manifold Prior [][] 🔹
• [Link] 3D Point Cloud Denoising Using a Joint Geometry and Color k-NN Graph 🔹
• [Link] Learning Graph-Convolutional Representations for Point Cloud Denoising [code] 🔥
• [Link] Differentiable Manifold Reconstruction for Point Cloud Denoising [code] 🔥
• [Link] Deep Point Set Resampling via Gradient Fields [code] 🔸
• [Link] Dynamic Point Cloud Denoising via Manifold-to Manifold Distance [][] 🔸

2021

• [Link] Score-Based Point Cloud Denoising [code] 🔥
• [Link] RePCD-Net: Feature-Aware Recurrent Point Cloud Denoising Network [code] 🔸
• [Link] VIPDA: A Visually Driven Point Cloud Denoising Algorithm Based on Anisotropic Point Cloud Filtering [][] ◼️
• [Link] Mesh Total Generalized Variation for Denoising [][] 🔹
• [Link] Exploiting color for graph-based 3D point cloud denoising [][] 🔹
• [Link] PCA-Based Denoising Algorithm for Outdoor Lidar Point Cloud Data [][] 🔹
• [Link] Anisotropic Denoising of 3D Point Clouds by Aggregation of Multiple Surface-Adaptive Estimates [][] 🔹
• [Link] Joint Geometry and Color Point Cloud Denoising Based on Graph Wavelets [][] 🔹
• [Link] Point cloud denoising using non-local collaborative projections [][] 🔹

2022

• [Link] Single-Stage Adaptive Multi-Scale Point Cloud Noise Filtering Algorithm Based on Feature Information 🔹
• [Link] GeoGCN: Geometric Dual-domain Graph Convolution Network for Point Cloud Denoising ◼️
• [Link] TDNet: transformer-based network for point cloud denoising 🔹
• [Link] PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows [code] dl. 🔹
• [Link] Point cloud denoising algorithm with geometric feature preserving ◼️
• [Link] Point Cloud Upsampling Algorithm: A Systematic Review surv. 🔹
• [Link] Dynamic Point Cloud Denoising via Gradient Fields ◼
• [Link] Structure-Aware Denoising for Real-world Noisy Point Clouds with Complex Structures 🔹
• [Link] From Noise Addition to Denoising: A Self-Variation Capture Network for Point Cloud Optimization ◼️
• [Link] MODNet: Multi-offset Point Cloud Denoising Network Customized for Multi-scale Patches [code] ◼️
• [Link] Denoising for 3D Point Cloud Based on Regularization of a Statistical Low-Dimensional Manifold ◼️
• [Link] Reflective Noise Filtering of Large-Scale Point Cloud Using Transformer 🔹
• [Link] Optimization of point cloud preprocessing algorithm for equipped vehicles ◼️
• [Link] Motion estimation and filtered prediction for dynamic point cloud attribute compression ◼️
• [Link] Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis surv. 🔥
• [Link] A Method Based on Improved iForest for Trunk Extraction and Denoising of Individual Street Trees 🔹

2023

• [Link] Contrastive Learning for Joint Normal Estimation and Point Cloud Filtering [code] 🔹
• [Link] Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds [code] 🔹
• [Link] Point Cloud Denoising Algorithm via Geometric Metrics on the Statistical Manifold ◼️
• [Link] Optimization of point cloud preprocessing algorithm for equipped vehicles ◼️
• [Link] 4DenoiseNet: Adverse Weather Denoising From Adjacent Point Clouds [code] 🔸
• [Link] 3D Point Cloud Denoising Algorithm Based on Two-Stage Filtering ◼️
• [Link] Attention Mechanism-based Deep Learning Denoising of Scanned Point Cloud for Rocket Tank Panel ◼️
• [Link] NoiseTrans: Point Cloud Denoising with Transformers ◼️
• [Link] A single-stage point cloud cleaning network for outlier removal and denoising 🔹
• [Link] GeoDualCNN: Geometry Supporting Dual Convolutional Neural Network for Noisy Point Clouds 🔹
• [Link] MSaD-Net: A Mix Self-Attention Networks for 3D Point Cloud Denoising
• [Link] Parameter optimization for point clouds denoising based on no-reference quality assessment 🔹
• [Link] Multiscale Feature Fusion for the Multistage Denoising of Airborne Single Photon LiDAR 🔹
• [Link] Bilateral filter denoising of Lidar point cloud data in automatic driving scene 🔹
• [Link] PCDNF: Revisiting Learning-based Point Cloud Denoising via Joint Normal Filtering [code] 🔹
• [Link] Point Cloud Denoising via Momentum Ascent in Gradient Fields [code] 🔹
• [Link] 3D point cloud global denoising algorithm based on different noise characteristics ◼️
• [Link] 3D point cloud denoising using anisotropic neighborhoods and a novel sharp feature detection algorithm [code] 🔹
• [Link] IterativePFN: True Iterative Point Cloud Filtering [code] 🔹
• [Link] Graph-Based Point Cloud Color Denoising with 3-Dimensional Patch-Based Similarity ◼️
• [Link] Deep learning-based point cloud upsampling: a review of recent trends surv. ◼️
• [Link] 3D point cloud denoising method based on global feature guidance ◼️

2024

• [Link] Fast graph-based denoising point cloud color information ◼️
• [Link] Three-Dimensional Point Cloud Denoising for Tunnel Data by Combining Intensity and Geometry Information ◼️
• [Link] PointCVaR: Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification [code] ◼️
• [Link] Point Cloud Denoising in Outdoor Real-World Scenes Based on Measurable Segmentation ◼️
• [Link] Transformer-based Point Cloud Denoising Network ◼️
• [Link] 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering
• [Link] PathNet: Path-Selective Point Cloud Denoising [code] 🔹
• [Link] The implementation method of point cloud denoising filter based on KinectV2 ◼️
• [Link] Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network [code] ◼️
• [Link] Self-supervised multi-echo point cloud denoising in snowfall [code] ◼️
• [Link] Denoising point clouds with fewer learnable parameters ◼️
• [Link] Review of 3D Point Cloud Processing Methods Based on Deep Learning surv. ◼️
• [Link] A Novel Point Cloud Adaptive Filtering Algorithm for LiDAR SLAMinForest Environments Based on Guidance Information ◼️
• [Link] StraightPCF: Straight Point Cloud Filtering [code] ◼️
• [Link] Deep Learning for 3D Point Cloud Enhancement: A Survey surv. ◼️
• [Link] TripleMixer A 3D Point Cloud Denoising Model or Adverse Weather [code] ◼️
• [Link] P2P-Bridge Diffusion Bridges for 3D Point Cloud [code] ◼️
• [Link] TPDNet: A point cloud data denoising method for offshore drilling platforms and its application ◼️
• [Link] Noise4Denoise: Leveraging Noise for Unsupervised Point Cloud Denoising ◼️

2025

...