mlsanityData to 14 Oct 2026

Deep Point Cloud Reconstruction

arXiv 2111.11704 ↗First posted 23 Nov 2021cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. In this paper, we advocate that jointly solving these tasks leads to significant improvement for point cloud reconstruction. To this end, we propose a deep point cloud reconstruction network consisting of two stages: 1) a 3D sparse stacked-hourglass network as for the initial densification and denoising, 2) a refinement via transformers converting the discrete voxels into 3D points. In particular, we further improve the performance of transformer by a newly proposed module called amplified positional encoding. This module has been designed to differently amplify the magnitude of positional encoding vectors based on the points' distances for adaptive refinements. Extensive experiments demonstrate that our network achieves state-of-the-art performance among the recent studies in the ScanNet, ICL-NUIM, and ShapeNetPart datasets. Moreover, we underline the ability of our network to generalize toward real-world and unmet scenes.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 48 of its 75 references that are in the map. First posted on arXiv 23 Nov 2021.

Builds on

48 of 75 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  7. 2020Point Transformercited by 1,470
  8. 2018On the Spectral Bias of Neural Networkscited by 1,341
  9. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  10. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  11. 2020Neural Sparse Voxel Fieldscited by 959
  12. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
36 more
  1. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  2. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  3. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  4. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  5. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  6. 2018Pyramid Stereo Matching Networkcited by 489
  7. 2018PCN: Point Completion Networkcited by 384
  8. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  9. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  10. 2020Deep Global Registrationcited by 229
  11. 2017Submanifold Sparse Convolutional Networkscited by 223
  12. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  13. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  14. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  15. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
  16. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  17. 2018Generating 3D Adversarial Point Cloudscited by 144
  18. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  19. 2019DPSNet: End-to-end Deep Plane Sweep Stereocited by 115
  20. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  21. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  22. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  23. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  24. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  25. 2021Score-Based Point Cloud Denoisingcited by 83
  26. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  27. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  28. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  29. 2020Generative Sparse Detection Networks for 3D Single-shot Object Detectioncited by 69
  30. 2019Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaningcited by 58
  31. 2021VolumeFusion: Deep Depth Fusion for 3D Scene Reconstructioncited by 44
  32. 2020Learning Graph-Convolutional Representations for Point Cloud Denoisingcited by 40
  33. 2020PointTriNet: Learned Triangulation of 3D Point Setscited by 32
  34. 2020Learning Delaunay Surface Elements for Mesh Reconstructioncited by 23
  35. 2021Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimationcited by 15
  36. 2021Stereo Object Matching Networkcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 3; 2025: 6; 2026: 1.

15 papers.

Sort:

By area:

  1. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  2. 2022Towards Scale Balanced 6-DoF Grasp Detection in Cluttered Scenescited by 21
  3. 2025SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorizationcited by 21
  4. 2023SCP: Spherical-Coordinate-based Learned Point Cloud Compressioncited by 12
  5. 2025HORT: Monocular Hand-held Objects Reconstruction with Transformerscited by 11
  6. 2023Fine-grained Text and Image Guided Point Cloud Completion with CLIP Modelcited by 5
  7. 2024RayProNet: A Neural Point Field Framework for Radio Propagation Modeling in 3D Environmentscited by 4
  8. 2023D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstructioncited by 3
  9. 2024Multi-Type Point Cloud Autoencoder: A Complete Equivariant Embedding for Molecule Conformation and Posecited by 3
  10. 2025Re-Densification Meets Cross-Scale Propagation: Real-Time Neural Compression of LiDAR Point Cloudscited by 2
  11. 2025Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Drivingcited by 2
  12. 2025SVRecon: Sparse Voxel Rasterization for Surface Reconstructioncited by 2
3 more
  1. 2026Towards Practical Lossless Neural Compression for LiDAR Point Cloudscited by 1
  2. 2022Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operatorscited by 0
  3. 2025Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splattingcited by 0