# Neural Star Domain as Primitive Representation

arXiv: https://arxiv.org/abs/2010.11248 · HTML: https://mlsanity.com/paper/2010.11248/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 17 of 17)

- [Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks](https://mlsanity.com/paper/2103.10429/) (2021)
- [Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds](https://mlsanity.com/paper/2106.03437/) (2021)
- [D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts](https://mlsanity.com/paper/2301.11497/) (2023)
- [PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision](https://mlsanity.com/paper/2303.09554/) (2023)
- [Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance](https://mlsanity.com/paper/2302.14268/) (2023)
- [Marching-Primitives: Shape Abstraction from Signed Distance Function](https://mlsanity.com/paper/2303.13190/) (2023)
- [Discovering 3D Parts from Image Collections](https://mlsanity.com/paper/2107.13629/) (2021)
- [Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects](https://mlsanity.com/paper/2110.04411/) (2021)
- [MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation](https://mlsanity.com/paper/2208.08580/) (2022)
- [Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly](https://mlsanity.com/paper/2303.01999/) (2023)
- [DAE-Net: Deforming Auto-Encoder for fine-grained shape co-segmentation](https://mlsanity.com/paper/2311.13125/) (2023)
- [PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation](https://mlsanity.com/paper/2112.13942/) (2021)
- [SweepNet: Unsupervised Learning Shape Abstraction via Neural Sweepers](https://mlsanity.com/paper/2407.06305/) (2024)
- [The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference](https://mlsanity.com/paper/2106.12026/) (2021)
- [HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling](https://mlsanity.com/paper/2301.10460/) (2023)
- [A Review of Deep Learning-Powered Mesh Reconstruction Methods](https://mlsanity.com/paper/2303.02879/) (2023)
- [SHRED: 3D Shape Region Decomposition with Learned Local Operations](https://mlsanity.com/paper/2206.03480/) (2022)

## Abstract (arXiv)

Reconstructing 3D objects from 2D images is a fundamental task in computer vision. Accurate structured reconstruction by parsimonious and semantic primitive representation further broadens its application. When reconstructing a target shape with multiple primitives, it is preferable that one can instantly access the union of basic properties of the shape such as collective volume and surface, treating the primitives as if they are one single shape. This becomes possible by primitive representation with unified implicit and explicit representations. However, primitive representations in current approaches do not satisfy all of the above requirements at the same time. To solve this problem, we propose a novel primitive representation named neural star domain (NSD) that learns primitive shapes in the star domain. We show that NSD is a universal approximator of the star domain and is not only parsimonious and semantic but also an implicit and explicit shape representation. We demonstrate that our approach outperforms existing methods in image reconstruction tasks, semantic capabilities, and speed and quality of sampling high-resolution meshes.