# SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation

arXiv: https://arxiv.org/abs/2505.17721 · HTML: https://mlsanity.com/paper/2505.17721/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [3D Shape Generation and Completion through Point-Voxel Diffusion](https://mlsanity.com/paper/2104.03670/) (2021)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](https://mlsanity.com/paper/1906.12320/) (2019)
- [Adversarial Feature Learning](https://mlsanity.com/paper/1605.09782/) (2016)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [Large Scale Adversarial Representation Learning](https://mlsanity.com/paper/1907.02544/) (2019)
- [3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions](https://mlsanity.com/paper/1905.06292/) (2019)
- [PF-Net: Point Fractal Network for 3D Point Cloud Completion](https://mlsanity.com/paper/2003.00410/) (2020)
- [Repurposing GANs for One-shot Semantic Part Segmentation](https://mlsanity.com/paper/2103.04379/) (2021)
- [Generative Hierarchical Features from Synthesizing Images](https://mlsanity.com/paper/2007.10379/) (2020)
- [Diffusion Models and Representation Learning: A Survey](https://mlsanity.com/paper/2407.00783/) (2024)
- [IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning](https://mlsanity.com/paper/2003.02920/) (2020)
- [Self-positioning Point-based Transformer for Point Cloud Understanding](https://mlsanity.com/paper/2303.16450/) (2023)
- [DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion](https://mlsanity.com/paper/2305.01921/) (2023)
- [DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation](https://mlsanity.com/paper/2008.05440/) (2020)
- [SPAGHETTI: Editing Implicit Shapes Through Part Aware Generation](https://mlsanity.com/paper/2201.13168/) (2022)
- [Linear Semantics in Generative Adversarial Networks](https://mlsanity.com/paper/2104.00487/) (2021)
- [SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation](https://mlsanity.com/paper/2108.04476/) (2021)

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

- [SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding](https://mlsanity.com/paper/2505.22643/) (2025)
- [Symmetry Matters: Auditing and Symmetrizing 3D Generative Models](https://mlsanity.com/paper/2512.18953/) (2025)
- [ISAP-3D: Identity-Slot Aligned Part-Aware 3D Generation](https://mlsanity.com/paper/2606.12099/) (2026)
- [FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows](https://mlsanity.com/paper/2607.26645/) (2026)

## Abstract (arXiv)

Denoising diffusion probabilistic models have achieved significant success in point cloud generation, enabling numerous downstream applications, such as generative data augmentation and 3D model editing. However, little attention has been given to generating point clouds with point-wise segmentation labels, as well as to developing evaluation metrics for this task. Therefore, in this paper, we present SeaLion, a novel diffusion model designed to generate high-quality and diverse point clouds with fine-grained segmentation labels. Specifically, we introduce the semantic part-aware latent point diffusion technique, which leverages the intermediate features of the generative models to jointly predict the noise for perturbed latent points and associated part segmentation labels during the denoising process, and subsequently decodes the latent points to point clouds conditioned on part segmentation labels. To effectively evaluate the quality of generated point clouds, we introduce a novel point cloud pairwise distance calculation method named part-aware Chamfer distance (p-CD). This method enables existing metrics, such as 1-NNA, to measure both the local structural quality and inter-part coherence of generated point clouds. Experiments on the large-scale synthetic dataset ShapeNet and real-world medical dataset IntrA demonstrate that SeaLion achieves remarkable performance in generation quality and diversity, outperforming the existing state-of-the-art model, DiffFacto, by 13.33% and 6.52% on 1-NNA (p-CD) across the two datasets. Experimental analysis shows that SeaLion can be trained semi-supervised, thereby reducing the demand for labeling efforts. Lastly, we validate the applicability of SeaLion in generative data augmentation for training segmentation models and the capability of SeaLion to serve as a tool for part-aware 3D shape editing.