# Temporal Point Cloud Completion with Pose Disturbance

arXiv: https://arxiv.org/abs/2202.03084 · HTML: https://mlsanity.com/paper/2202.03084/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 7 Feb 2022.

## Builds on (most cited first, 30 of 30)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (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)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [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)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [DeepMVS: Learning Multi-view Stereopsis](https://mlsanity.com/paper/1804.00650/) (2018)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing](https://mlsanity.com/paper/1911.13225/) (2019)
- [GRNet: Gridding Residual Network for Dense Point Cloud Completion](https://mlsanity.com/paper/2006.03761/) (2020)
- [Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence](https://mlsanity.com/paper/2011.13650/) (2020)
- [Point Cloud Completion by Skip-attention Network with Hierarchical Folding](https://mlsanity.com/paper/2005.03871/) (2020)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths](https://mlsanity.com/paper/2012.03408/) (2020)
- [High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference](https://mlsanity.com/paper/1709.07599/) (2017)
- [Learning Deformable Tetrahedral Meshes for 3D Reconstruction](https://mlsanity.com/paper/2011.01437/) (2020)
- [Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding](https://mlsanity.com/paper/2103.07838/) (2021)
- [View-Guided Point Cloud Completion](https://mlsanity.com/paper/2104.05666/) (2021)
- [Style-based Point Generator with Adversarial Rendering for Point Cloud Completion](https://mlsanity.com/paper/2103.02535/) (2021)
- [Self-Supervised Deep Visual Odometry with Online Adaptation](https://mlsanity.com/paper/2005.06136/) (2020)
- [Weakly-supervised 3D Shape Completion in the Wild](https://mlsanity.com/paper/2008.09110/) (2020)
- [ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion](https://mlsanity.com/paper/2104.09587/) (2021)
- [Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry](https://mlsanity.com/paper/1904.01892/) (2019)
- [Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences](https://mlsanity.com/paper/2103.06028/) (2021)
- [3D Reconstruction of Novel Object Shapes from Single Images](https://mlsanity.com/paper/2006.07752/) (2020)
- [Interactive Annotation of 3D Object Geometry using 2D Scribbles](https://mlsanity.com/paper/2008.10719/) (2020)
- [P2P-NET: Bidirectional Point Displacement Net for Shape Transform](https://mlsanity.com/paper/1803.09263/) (2018)
- [Graph-Guided Deformation for Point Cloud Completion](https://mlsanity.com/paper/2112.01840/) (2021)

## Built on by (most cited first, 5 of 5)

- [Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis](https://mlsanity.com/paper/2203.03311/) (2022)
- [SCARP: 3D Shape Completion in ARbitrary Poses for Improved Grasping](https://mlsanity.com/paper/2301.07213/) (2023)
- [US-X Complete: A Multi-Modal Approach to Anatomical 3D Shape Recovery](https://mlsanity.com/paper/2511.15600/) (2025)
- [NeRF2Points: Large-Scale Point Cloud Generation From Street Views' Radiance Field Optimization](https://mlsanity.com/paper/2404.04875/) (2024)
- [Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completion](https://mlsanity.com/paper/2303.01804/) (2023)

## Abstract (arXiv)

Point clouds collected by real-world sensors are always unaligned and sparse, which makes it hard to reconstruct the complete shape of object from a single frame of data. In this work, we manage to provide complete point clouds from sparse input with pose disturbance by limited translation and rotation. We also use temporal information to enhance the completion model, refining the output with a sequence of inputs. With the help of gated recovery units(GRU) and attention mechanisms as temporal units, we propose a point cloud completion framework that accepts a sequence of unaligned and sparse inputs, and outputs consistent and aligned point clouds. Our network performs in an online manner and presents a refined point cloud for each frame, which enables it to be integrated into any SLAM or reconstruction pipeline. As far as we know, our framework is the first to utilize temporal information and ensure temporal consistency with limited transformation. Through experiments in ShapeNet and KITTI, we prove that our framework is effective in both synthetic and real-world datasets.