PCN: Point Completion Network
Not on the map. Why?
Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.
Abstract (arXiv)
Shape completion, the problem of estimating the complete geometry of objects from partial observations, lies at the core of many vision and robotics applications. In this work, we propose Point Completion Network (PCN), a novel learning-based approach for shape completion. Unlike existing shape completion methods, PCN directly operates on raw point clouds without any structural assumption (e.g. symmetry) or annotation (e.g. semantic class) about the underlying shape. It features a decoder design that enables the generation of fine-grained completions while maintaining a small number of parameters. Our experiments show that PCN produces dense, complete point clouds with realistic structures in the missing regions on inputs with various levels of incompleteness and noise, including cars from LiDAR scans in the KITTI dataset.
Key facts. Cited by 382 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Aug 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 64; 2022: 94; 2023: 60; 2024: 63; 2025: 62; 2026: 39.
382 papers.
Sort:
By area:
- 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
- 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
- 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
- 2021Multimodal Virtual Point 3D Detectioncited by 166
- 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
- 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
- 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 111
- 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
- 2021Variational Relational Point Completion Networkcited by 103
- 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
- 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
- 2022POCO: Point Convolution for Surface Reconstructioncited by 91
38 more
- 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
- 20213D Semantic Scene Completion: a Surveycited by 74
- 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
- 2022ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfercited by 73
- 2021SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elementscited by 72
- 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
- 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
- 2022ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimizationcited by 70
- 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 69
- 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 68
- 2023AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformerscited by 65
- 2021RGB-D Local Implicit Function for Depth Completion of Transparent Objectscited by 64
- 2023DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objectscited by 64
- 2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
- 2021Semantic Scene Completion via Integrating Instances and Scene in-the-Loopcited by 54
- 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
- 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
- 2022Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fieldscited by 53
- 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
- 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 49
- 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
- 2021View-Guided Point Cloud Completioncited by 46
- 2022Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learningcited by 46
- 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 46
- 2021Style-based Point Generator with Adversarial Rendering for Point Cloud Completioncited by 45
- 20223D Shape Reconstruction from 2D Images with Disentangled Attribute Flowcited by 45
- 2022Equivariant Transporter Networkcited by 44
- 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
- 2022PointAttN: You Only Need Attention for Point Cloud Completioncited by 43
- 2023ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformercited by 43
- 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
- 2021GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completioncited by 41
- 2023The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objectscited by 40
- 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
- 2023Point-Cloud Completion with Pretrained Text-to-image Diffusion Modelscited by 37
- 2022Cross-modal Learning for Image-Guided Point Cloud Shape Completioncited by 36
- 2021Active 3D Shape Reconstruction from Vision and Touchcited by 34
- 2023SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generatorcited by 34
50 most cited of 382 All 382 (JSON)
- 2026TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception25 Sep 2026
- 2026ZVeC: A Zero-Shot Framework for Instance-Level Vehicle Extraction and Generative Point Cloud Completion21 Sep 2026
- 2026ScaleBlind: Point Cloud Completion under Unknown Scale20 Sep 2026
- 2026UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound10 Sep 2026
- 2026GSComplete: Gaussian Splat Completion with 2D Diffusion Priors8 Sep 2026
- 2026Learning-Based Reconstruction Attacks on Coordinate-Obfuscated Point Clouds2 Sep 2026
- 2026DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic Perception31 Aug 2026
- 2026Denoising-Aware Temporal Point Cloud Completion for 3D Crop Architecture Recovery and Phenotypic Trait Extraction28 Aug 2026
- 2026Hyper^2: Unleashing Hyperbolic Geometry's Full Potential via Dual-Space Consistency23 Aug 2026
- 2026A Strong Linear Baseline for Whole-Heart Cardiac Shape Completion on CT, with an Open Eleven-Structure Statistical Shape Model20 Aug 2026
- 2026Towards Real-Time and Adaptable LiDAR Scene Completion17 Aug 2026
- 2026GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure14 Aug 2026
38 more
- 2026SUMI: Scalable Unified Model for 3D Point Cloud Inference8 Aug 2026
- 2026FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows29 Jul 2026
- 2026Physics-inspired Pseudo Anomaly Generation and Prototype Feature Guidance for 3D Anomaly Detection12 Jul 2026
- 2026MAGE: View-guided Point Cloud Completion with Efficient Modality Alignment and Adaptive Geometry Enhancement30 Jun 2026
- 20263D Point World Models: Point Completion Enables More Accurate Dynamics Learning30 Jun 2026
- 2026Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms23 Jun 2026
- 2026CAOA -- Completion-Assisted Object-CAD Alignment16 Jun 2026
- 2026DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models26 May 2026
- 2026I2PRef: Image-Driven Point Completion with Iterative Refinement26 May 2026
- 2026ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation25 May 2026
- 2026PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration24 May 2026
- 2026The Observable Wasserstein Distance11 May 2026
- 2026SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion2 May 2026
- 2026InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization1 May 2026
- 2026DOT-Sim: Differentiable Optical Tactile Simulation with Precise Real-to-Sim Physical Calibration30 Apr 2026
- 2026TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches10 Apr 2026
- 2026Generative Shape Reconstruction with Geometry-Guided Langevin Dynamics27 Mar 2026
- 2026From Synthetic Data to Real Restorations: Diffusion Model for Patient-specific Dental Crown Completion27 Mar 2026
- 2026GGPT: Geometry Grounded Point Transformer11 Mar 2026
- 2026MADCrowner: Margin Aware Dental Crown Design with Template Deformation and Refinement5 Mar 2026
- 2026PPC-MT: Parallel Point Cloud Completion with Mamba-Transformer Hybrid Architecture1 Mar 2026
- 2026BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds27 Feb 2026
- 2026LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency21 Feb 2026
- 2026REVNET: Rotation-Equivariant Point Cloud Completion via Vector Neuron Anchor Transformer13 Jan 2026
- 2026MGPC: Multimodal Network for Generalizable Point Cloud Completion With Modality Dropout and Progressive Decoding7 Jan 2026
- 2026Unified Primitive Proxies for Structured Shape Completion2 Jan 2026
- 2026Mask-Conditioned Voxel Diffusion for Joint Geometry and Color Inpainting1 Jan 2026
- 2025From Theory to Throughput: CUDA-Optimized APML for Large-Batch 3D Learning17 Dec 2025
- 2025Repurposing 2D Diffusion Models for 3D Shape Completion16 Dec 2025
- 2025TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decoder12 Dec 2025
- 2025Manifold-Aware Point Cloud Completion via Geodesic-Attentive Hierarchical Feature Learning5 Dec 2025
- 2025Object Reconstruction under Occlusion with Generative Priors and Contact-induced Constraints4 Dec 2025
- 2025Memory-Guided Point Cloud Completion for Dental Reconstruction3 Dec 2025
- 2025SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting2 Dec 2025
- 2025HeartFormer: Semantic-Aware Dual-Structure Transformers for 3D Four-Chamber Cardiac Point Cloud Reconstruction29 Nov 2025
- 2025DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion25 Nov 2025
- 2025QAL: A Loss for Recall Precision Balance in 3D Reconstruction21 Nov 2025
- 2025RL-AD-Net: Reinforcement Learning Guided Adaptive Displacement in Latent Space for Refined Point Cloud Completion21 Nov 2025
50 newest of 382 All 382 (JSON)
- 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
- 2023Point-Cloud Completion with Pretrained Text-to-image Diffusion Modelscited by 37
- 2024PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priorscited by 16
- 2024SC-Diff: 3D Shape Completion with Latent Diffusion Modelscited by 10
- 2024Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generationcited by 6
- 2024ComPC: Completing a 3D Point Cloud with 2D Diffusion Priorscited by 6
- 2024Multi-scale Latent Point Consistency Models for 3D Shape Generationcited by 6
- 2025DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completioncited by 5
- 2024PointDreamer: Zero-shot 3D Textured Mesh Reconstruction from Colored Point Cloudcited by 3
- 20253D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planningcited by 1
- 2025Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Imagecited by 1
- 2025Repurposing 2D Diffusion Models for 3D Shape Completioncited by 1
12 most cited of 18 All 18 (JSON)
- 2026GSComplete: Gaussian Splat Completion with 2D Diffusion Priors8 Sep 2026
- 2026InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization1 May 2026
- 2026TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches10 Apr 2026
- 2026From Synthetic Data to Real Restorations: Diffusion Model for Patient-specific Dental Crown Completion27 Mar 2026
- 2026BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds27 Feb 2026
- 2025Repurposing 2D Diffusion Models for 3D Shape Completion16 Dec 2025
- 2025Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image14 Nov 2025
- 20253D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning3 Oct 2025
- 2025DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completion28 Sep 2025
- 2024Multi-scale Latent Point Consistency Models for 3D Shape Generation27 Dec 2024
- 2024PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors28 Nov 2024
- 2024RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models16 Sep 2024
12 newest of 18 All 18 (JSON)
- 2025SRMamba: Mamba for Super-Resolution of LiDAR Point Cloudscited by 5
- 2025MambaTron: Efficient Cross-Modal Point Cloud Enhancement using Aggregate Selective State Space Modelingcited by 2
- 2025DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completioncited by 2
- 2026PPC-MT: Parallel Point Cloud Completion with Mamba-Transformer Hybrid Architecturecited by 1
- 2026PPC-MT: Parallel Point Cloud Completion with Mamba-Transformer Hybrid Architecture1 Mar 2026
- 2025DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion25 Nov 2025
- 2025SRMamba: Mamba for Super-Resolution of LiDAR Point Clouds15 May 2025
- 2025MambaTron: Efficient Cross-Modal Point Cloud Enhancement using Aggregate Selective State Space Modeling25 Jan 2025
- 2025SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorizationcited by 20
- 2025LiDPM: Rethinking Point Diffusion for Lidar Scene Completioncited by 10
- 20263D Point World Models: Point Completion Enables More Accurate Dynamics Learningcited by 1
- 2026TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perceptioncited by 0
- 2026TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception25 Sep 2026
- 20263D Point World Models: Point Completion Enables More Accurate Dynamics Learning30 Jun 2026
- 2025LiDPM: Rethinking Point Diffusion for Lidar Scene Completion24 Apr 2025
- 2025SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization18 Mar 2025
- 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
- 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
- 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
- 2021Multimodal Virtual Point 3D Detectioncited by 166
- 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
- 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
- 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 111
- 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
- 2021Variational Relational Point Completion Networkcited by 103
- 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
- 2022POCO: Point Convolution for Surface Reconstructioncited by 91
- 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
12 most cited of 356 All 356 (JSON)
- 2026ZVeC: A Zero-Shot Framework for Instance-Level Vehicle Extraction and Generative Point Cloud Completion21 Sep 2026
- 2026ScaleBlind: Point Cloud Completion under Unknown Scale20 Sep 2026
- 2026UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound10 Sep 2026
- 2026Learning-Based Reconstruction Attacks on Coordinate-Obfuscated Point Clouds2 Sep 2026
- 2026DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic Perception31 Aug 2026
- 2026Denoising-Aware Temporal Point Cloud Completion for 3D Crop Architecture Recovery and Phenotypic Trait Extraction28 Aug 2026
- 2026Hyper^2: Unleashing Hyperbolic Geometry's Full Potential via Dual-Space Consistency23 Aug 2026
- 2026A Strong Linear Baseline for Whole-Heart Cardiac Shape Completion on CT, with an Open Eleven-Structure Statistical Shape Model20 Aug 2026
- 2026Towards Real-Time and Adaptable LiDAR Scene Completion17 Aug 2026
- 2026GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure14 Aug 2026
- 2026SUMI: Scalable Unified Model for 3D Point Cloud Inference8 Aug 2026
- 2026FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows29 Jul 2026
12 newest of 356 All 356 (JSON)