# Deep Point Cloud Reconstruction

arXiv: https://arxiv.org/abs/2111.11704 · HTML: https://mlsanity.com/paper/2111.11704/

## 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 (most cited first, 30 of 48)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)
- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)
- [PF-Net: Point Fractal Network for 3D Point Cloud Completion](https://mlsanity.com/paper/2003.00410/) (2020)
- [Generating 3D Adversarial Point Clouds](https://mlsanity.com/paper/1809.07016/) (2018)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)

## Built on by (most cited first, 15 of 15)

- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Towards Scale Balanced 6-DoF Grasp Detection in Cluttered Scenes](https://mlsanity.com/paper/2212.05275/) (2022)
- [SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization](https://mlsanity.com/paper/2503.14558/) (2025)
- [SCP: Spherical-Coordinate-based Learned Point Cloud Compression](https://mlsanity.com/paper/2308.12535/) (2023)
- [HORT: Monocular Hand-held Objects Reconstruction with Transformers](https://mlsanity.com/paper/2503.21313/) (2025)
- [Fine-grained Text and Image Guided Point Cloud Completion with CLIP Model](https://mlsanity.com/paper/2308.08754/) (2023)
- [RayProNet: A Neural Point Field Framework for Radio Propagation Modeling in 3D Environments](https://mlsanity.com/paper/2406.16907/) (2024)
- [D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction](https://mlsanity.com/paper/2311.14189/) (2023)
- [Multi-Type Point Cloud Autoencoder: A Complete Equivariant Embedding for Molecule Conformation and Pose](https://mlsanity.com/paper/2405.13791/) (2024)
- [Re-Densification Meets Cross-Scale Propagation: Real-Time Neural Compression of LiDAR Point Clouds](https://mlsanity.com/paper/2508.20466/) (2025)
- [Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving](https://mlsanity.com/paper/2509.13116/) (2025)
- [SVRecon: Sparse Voxel Rasterization for Surface Reconstruction](https://mlsanity.com/paper/2511.17364/) (2025)
- [Towards Practical Lossless Neural Compression for LiDAR Point Clouds](https://mlsanity.com/paper/2603.25260/) (2026)
- [Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators](https://mlsanity.com/paper/2205.01087/) (2022)
- [Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting](https://mlsanity.com/paper/2512.20927/) (2025)

## 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.