# Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism

arXiv: https://arxiv.org/abs/2203.10569 · HTML: https://mlsanity.com/paper/2203.10569/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 20 Mar 2022.

## Builds on (most cited first, 23 of 23)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [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)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [GRNet: Gridding Residual Network for Dense Point Cloud Completion](https://mlsanity.com/paper/2006.03761/) (2020)
- [PF-Net: Point Fractal Network for 3D Point Cloud Completion](https://mlsanity.com/paper/2003.00410/) (2020)
- [Cascaded Refinement Network for Point Cloud Completion](https://mlsanity.com/paper/2004.03327/) (2020)
- [Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints](https://mlsanity.com/paper/1910.06727/) (2019)
- [3D Point Capsule Networks](https://mlsanity.com/paper/1812.10775/) (2018)
- [Point Cloud Completion by Skip-attention Network with Hierarchical Folding](https://mlsanity.com/paper/2005.03871/) (2020)
- [Detail Preserved Point Cloud Completion via Separated Feature Aggregation](https://mlsanity.com/paper/2007.02374/) (2020)
- [Unsupervised 3D Shape Completion through GAN Inversion](https://mlsanity.com/paper/2104.13366/) (2021)
- [Unpaired Point Cloud Completion on Real Scans using Adversarial Training](https://mlsanity.com/paper/1904.00069/) (2019)
- [Multimodal Shape Completion via Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2003.07717/) (2020)
- [RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion](https://mlsanity.com/paper/1904.12304/) (2019)
- [Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding](https://mlsanity.com/paper/2103.07838/) (2021)
- [AADS: Augmented Autonomous Driving Simulation using Data-driven Algorithms](https://mlsanity.com/paper/1901.07849/) (2019)
- [Skeleton-bridged Point Completion: From Global Inference to Local Adjustment](https://mlsanity.com/paper/2010.07428/) (2020)
- [Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation](https://mlsanity.com/paper/2103.14269/) (2021)

## Built on by (most cited first, 3 of 3)

- [Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey](https://mlsanity.com/paper/2305.04691/) (2023)
- [P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds](https://mlsanity.com/paper/2307.14726/) (2023)
- [US-X Complete: A Multi-Modal Approach to Anatomical 3D Shape Recovery](https://mlsanity.com/paper/2511.15600/) (2025)

## Abstract (arXiv)

Real scans always miss partial geometries of objects due to the self-occlusions, external-occlusions, and limited sensor resolutions. Point cloud completion aims to refer the complete shapes for incomplete 3D scans of objects. Current deep learning-based approaches rely on large-scale complete shapes in the training process, which are usually obtained from synthetic datasets. It is not applicable for real-world scans due to the domain gap. In this paper, we propose a self-supervised point cloud completion method (TraPCC) for vehicles in real traffic scenes without any complete data. Based on the symmetry and similarity of vehicles, we make use of consecutive point cloud frames to construct vehicle memory bank as reference. We design a bottom-up mechanism to focus on both local geometry details and global shape features of inputs. In addition, we design a scene-graph in the network to pay attention to the missing parts by the aid of neighboring vehicles. Experiments show that TraPCC achieve good performance for real-scan completion on KITTI and nuScenes traffic datasets even without any complete data in training. We also show a downstream application of 3D detection, which benefits from our completion approach.