# SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification

arXiv: https://arxiv.org/abs/2008.07358 · HTML: https://mlsanity.com/paper/2008.07358/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2020.

## Built on by (most cited first, 30 of 33)

- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)
- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths](https://mlsanity.com/paper/2202.09507/) (2022)
- [Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis](https://mlsanity.com/paper/2203.03311/) (2022)
- [PointAttN: You Only Need Attention for Point Cloud Completion](https://mlsanity.com/paper/2203.08485/) (2022)
- [3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views](https://mlsanity.com/paper/2406.04875/) (2024)
- [Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer](https://mlsanity.com/paper/2202.09367/) (2022)
- [Voxel-based Network for Shape Completion by Leveraging Edge Generation](https://mlsanity.com/paper/2108.09936/) (2021)
- [ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion](https://mlsanity.com/paper/2104.09587/) (2021)
- [FBNet: Feedback Network for Point Cloud Completion](https://mlsanity.com/paper/2210.03974/) (2022)
- [From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction](https://mlsanity.com/paper/2203.08122/) (2022)
- [ME-PCN: Point Completion Conditioned on Mask Emptiness](https://mlsanity.com/paper/2108.08187/) (2021)
- [Denoise and Contrast for Category Agnostic Shape Completion](https://mlsanity.com/paper/2103.16671/) (2021)
- [Self-Supervised Point Cloud Completion via Inpainting](https://mlsanity.com/paper/2111.10701/) (2021)
- [Learning Local Displacements for Point Cloud Completion](https://mlsanity.com/paper/2203.16600/) (2022)
- [Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning](https://mlsanity.com/paper/2112.05213/) (2021)
- [CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm](https://mlsanity.com/paper/2207.05359/) (2022)
- [SCoDA: Domain Adaptive Shape Completion for Real Scans](https://mlsanity.com/paper/2304.10179/) (2023)
- [Attention-based Transformation from Latent Features to Point Clouds](https://mlsanity.com/paper/2112.05324/) (2021)
- [SCARP: 3D Shape Completion in ARbitrary Poses for Improved Grasping](https://mlsanity.com/paper/2301.07213/) (2023)
- [SoftPool++: An Encoder-Decoder Network for Point Cloud Completion](https://mlsanity.com/paper/2205.03899/) (2022)
- [FSC: Few-point Shape Completion](https://mlsanity.com/paper/2403.07359/) (2024)
- [Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion](https://mlsanity.com/paper/2204.09186/) (2022)
- [Deep Learning for 3D Point Cloud Enhancement: A Survey](https://mlsanity.com/paper/2411.00857/) (2024)
- [High-Fidelity Point Cloud Completion with Low-Resolution Recovery and Noise-Aware Upsampling](https://mlsanity.com/paper/2112.11271/) (2021)
- [HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity](https://mlsanity.com/paper/2506.23854/) (2025)
- [SRPCN: Structure Retrieval based Point Completion Network](https://mlsanity.com/paper/2202.02669/) (2022)
- [Point cloud completion via structured feature maps using a feedback network](https://mlsanity.com/paper/2202.08583/) (2022)
- [Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation](https://mlsanity.com/paper/2203.09772/) (2022)
- [Prototype-Aware Heterogeneous Task for Point Cloud Completion](https://mlsanity.com/paper/2209.01733/) (2022)

## Abstract (arXiv)

Point clouds are often the default choice for many applications as they exhibit more flexibility and efficiency than volumetric data. Nevertheless, their unorganized nature -- points are stored in an unordered way -- makes them less suited to be processed by deep learning pipelines. In this paper, we propose a method for 3D object completion and classification based on point clouds. We introduce a new way of organizing the extracted features based on their activations, which we name soft pooling. For the decoder stage, we propose regional convolutions, a novel operator aimed at maximizing the global activation entropy. Furthermore, inspired by the local refining procedure in Point Completion Network (PCN), we also propose a patch-deforming operation to simulate deconvolutional operations for point clouds. This paper proves that our regional activation can be incorporated in many point cloud architectures like AtlasNet and PCN, leading to better performance for geometric completion. We evaluate our approach on different 3D tasks such as object completion and classification, achieving state-of-the-art accuracy.