# Cross-Shape Attention for Part Segmentation of 3D Point Clouds

arXiv: https://arxiv.org/abs/2003.09053 · HTML: https://mlsanity.com/paper/2003.09053/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [Find Any Part in 3D](https://mlsanity.com/paper/2411.13550/) (2024)
- [DexVLG: Dexterous Vision-Language-Grasp Model at Scale](https://mlsanity.com/paper/2507.02747/) (2025)
- [SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation](https://mlsanity.com/paper/2512.16143/) (2025)
- [Adaptive Scaling with Geometric and Visual Continuity of completed 3D objects](https://mlsanity.com/paper/2602.12905/) (2026)

## Abstract (arXiv)

We present a deep learning method that propagates point-wise feature representations across shapes within a collection for the purpose of 3D shape segmentation. We propose a cross-shape attention mechanism to enable interactions between a shape's point-wise features and those of other shapes. The mechanism assesses both the degree of interaction between points and also mediates feature propagation across shapes, improving the accuracy and consistency of the resulting point-wise feature representations for shape segmentation. Our method also proposes a shape retrieval measure to select suitable shapes for cross-shape attention operations for each test shape. Our experiments demonstrate that our approach yields state-of-the-art results in the popular PartNet dataset.