# CasPoinTr: Point Cloud Completion with Cascaded Networks and Knowledge Distillation

arXiv: https://arxiv.org/abs/2509.23375 · HTML: https://mlsanity.com/paper/2509.23375/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 29 of its 37 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 29 of 29)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [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)
- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)
- [Channel-wise Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/2011.13256/) (2020)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [PF-Net: Point Fractal Network for 3D Point Cloud Completion](https://mlsanity.com/paper/2003.00410/) (2020)
- [Cross-Layer Distillation with Semantic Calibration](https://mlsanity.com/paper/2012.03236/) (2020)
- [Cascaded Refinement Network for Point Cloud Completion](https://mlsanity.com/paper/2004.03327/) (2020)
- [Knowledge Adaptation for Efficient Semantic Segmentation](https://mlsanity.com/paper/1903.04688/) (2019)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer](https://mlsanity.com/paper/2207.10315/) (2022)
- [RGCNN: Regularized Graph CNN for Point Cloud Segmentation](https://mlsanity.com/paper/1806.02952/) (2018)
- [AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers](https://mlsanity.com/paper/2301.04545/) (2023)
- [RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion](https://mlsanity.com/paper/1904.12304/) (2019)
- [PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths](https://mlsanity.com/paper/2202.09507/) (2022)
- [3D-to-2D Distillation for Indoor Scene Parsing](https://mlsanity.com/paper/2104.02243/) (2021)
- [P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds](https://mlsanity.com/paper/2307.14726/) (2023)
- [Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation](https://mlsanity.com/paper/2203.11160/) (2022)
- [CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation](https://mlsanity.com/paper/2303.05620/) (2023)
- [Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection](https://mlsanity.com/paper/2210.05593/) (2022)
- [PointSSC: A Cooperative Vehicle-Infrastructure Point Cloud Benchmark for Semantic Scene Completion](https://mlsanity.com/paper/2309.12708/) (2023)
- [CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm](https://mlsanity.com/paper/2207.05359/) (2022)
- [Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion](https://mlsanity.com/paper/2204.09186/) (2022)
- [Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation](https://mlsanity.com/paper/2407.13254/) (2024)

## Abstract (arXiv)

Point clouds collected from real-world environments are often incomplete due to factors such as limited sensor resolution, single viewpoints, occlusions, and noise. These challenges make point cloud completion essential for various applications. A key difficulty in this task is predicting the overall shape and reconstructing missing regions from highly incomplete point clouds. To address this, we introduce CasPoinTr, a novel point cloud completion framework using cascaded networks and knowledge distillation. CasPoinTr decomposes the completion task into two synergistic stages: Shape Reconstruction, which generates auxiliary information, and Fused Completion, which leverages this information alongside knowledge distillation to generate the final output. Through knowledge distillation, a teacher model trained on denser point clouds transfers incomplete-complete associative knowledge to the student model, enhancing its ability to estimate the overall shape and predict missing regions. Together, the cascaded networks and knowledge distillation enhance the model's ability to capture global shape context while refining local details, effectively bridging the gap between incomplete inputs and complete targets. Experiments on ShapeNet-55 under different difficulty settings demonstrate that CasPoinTr outperforms existing methods in shape recovery and detail preservation, highlighting the effectiveness of our cascaded structure and distillation strategy.