# P2P-NET: Bidirectional Point Displacement Net for Shape Transform

arXiv: https://arxiv.org/abs/1803.09263 · HTML: https://mlsanity.com/paper/1803.09263/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2018.

## Built on by (most cited first, 11 of 11)

- [GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis](https://mlsanity.com/paper/2402.16994/) (2024)
- [SENS: Part-Aware Sketch-based Implicit Neural Shape Modeling](https://mlsanity.com/paper/2306.06088/) (2023)
- [PDT: Point Distribution Transformation with Diffusion Models](https://mlsanity.com/paper/2507.18939/) (2025)
- [Graph-Guided Deformation for Point Cloud Completion](https://mlsanity.com/paper/2112.01840/) (2021)
- [Temporal Point Cloud Completion with Pose Disturbance](https://mlsanity.com/paper/2202.03084/) (2022)
- [PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Sampling](https://mlsanity.com/paper/2202.10251/) (2022)
- [Shape Completion with Points in the Shadow](https://mlsanity.com/paper/2209.08345/) (2022)
- [TCFNet: Bidirectional face-bone transformation via a Transformer-based coarse-to-fine point movement network](https://mlsanity.com/paper/2508.14373/) (2025)
- [Rethinking Point Cloud Filtering: A Non-Local Position Based Approach](https://mlsanity.com/paper/2110.07253/) (2021)
- [Concept Activation Vectors for Generating User-Defined 3D Shapes](https://mlsanity.com/paper/2205.02102/) (2022)
- [Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completion](https://mlsanity.com/paper/2303.01804/) (2023)

## Abstract (arXiv)

We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e.g., meso-skeletons and surfaces, partial and complete scans, etc. The architecture of the P2P-NET is that of a bi-directional point displacement network, which transforms a source point set to a target point set with the same cardinality, and vice versa, by applying point-wise displacement vectors learned from data. P2P-NET is trained on paired shapes from the source and target domains, but without relying on point-to-point correspondences between the source and target point sets. The training loss combines two uni-directional geometric losses, each enforcing a shape-wise similarity between the predicted and the target point sets, and a cross-regularization term to encourage consistency between displacement vectors going in opposite directions. We develop and present several different applications enabled by our general-purpose bidirectional P2P-NET to highlight the effectiveness, versatility, and potential of our network in solving a variety of point-based shape transformation problems.