# 3D Shape Segmentation with Projective Convolutional Networks

arXiv: https://arxiv.org/abs/1612.02808 · HTML: https://mlsanity.com/paper/1612.02808/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2016.

## Built on by (most cited first, 30 of 63)

- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [SATR: Zero-Shot Semantic Segmentation of 3D Shapes](https://mlsanity.com/paper/2304.04909/) (2023)
- [Adaptive Graph Convolution for Point Cloud Analysis](https://mlsanity.com/paper/2108.08035/) (2021)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [A Survey on Deep Domain Adaptation for LiDAR Perception](https://mlsanity.com/paper/2106.02377/) (2021)
- [Segment Any Mesh](https://mlsanity.com/paper/2408.13679/) (2024)
- [PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning](https://mlsanity.com/paper/2112.05136/) (2021)
- [BuildingNet: Learning to Label 3D Buildings](https://mlsanity.com/paper/2110.04955/) (2021)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [Query2CAD: Generating CAD models using natural language queries](https://mlsanity.com/paper/2406.00144/) (2024)
- [PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation](https://mlsanity.com/paper/2312.04016/) (2023)
- [Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding](https://mlsanity.com/paper/2111.15363/) (2021)
- [3D Vision with Transformers: A Survey](https://mlsanity.com/paper/2208.04309/) (2022)
- [RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures](https://mlsanity.com/paper/2201.12763/) (2022)
- [Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis](https://mlsanity.com/paper/2212.08892/) (2022)
- [A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios](https://mlsanity.com/paper/2103.13109/) (2021)
- [LitePT: Lighter Yet Stronger Point Transformer](https://mlsanity.com/paper/2512.13689/) (2025)
- [Residual 3D Scene Flow Learning with Context-Aware Feature Extraction](https://mlsanity.com/paper/2109.04685/) (2021)
- [CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs](https://mlsanity.com/paper/2311.16703/) (2023)
- [Geometric Deep Learning for Computer-Aided Design: A Survey](https://mlsanity.com/paper/2402.17695/) (2024)
- [iSeg: Interactive 3D Segmentation via Interactive Attention](https://mlsanity.com/paper/2404.03219/) (2024)
- [AGConv: Adaptive Graph Convolution on 3D Point Clouds](https://mlsanity.com/paper/2206.04665/) (2022)
- [Neural Semantic Surface Maps](https://mlsanity.com/paper/2309.04836/) (2023)
- [Laplacian2Mesh: Laplacian-Based Mesh Understanding](https://mlsanity.com/paper/2202.00307/) (2022)
- [MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation](https://mlsanity.com/paper/2208.08580/) (2022)
- [SegNeRF: 3D Part Segmentation with Neural Radiance Fields](https://mlsanity.com/paper/2211.11215/) (2022)
- [Semi-supervised 3D shape segmentation with multilevel consistency and part substitution](https://mlsanity.com/paper/2204.08824/) (2022)
- [A Review of Panoptic Segmentation for Mobile Mapping Point Clouds](https://mlsanity.com/paper/2304.13980/) (2023)
- [Continuous Conditional Random Field Convolution for Point Cloud Segmentation](https://mlsanity.com/paper/2110.06085/) (2021)
- [MVTN: Learning Multi-View Transformations for 3D Understanding](https://mlsanity.com/paper/2212.13462/) (2022)

## Abstract (arXiv)

This paper introduces a deep architecture for segmenting 3D objects into their labeled semantic parts. Our architecture combines image-based Fully Convolutional Networks (FCNs) and surface-based Conditional Random Fields (CRFs) to yield coherent segmentations of 3D shapes. The image-based FCNs are used for efficient view-based reasoning about 3D object parts. Through a special projection layer, FCN outputs are effectively aggregated across multiple views and scales, then are projected onto the 3D object surfaces. Finally, a surface-based CRF combines the projected outputs with geometric consistency cues to yield coherent segmentations. The whole architecture (multi-view FCNs and CRF) is trained end-to-end. Our approach significantly outperforms the existing state-of-the-art methods in the currently largest segmentation benchmark (ShapeNet). Finally, we demonstrate promising segmentation results on noisy 3D shapes acquired from consumer-grade depth cameras.