# iSeg3D: An Interactive 3D Shape Segmentation Tool

arXiv: https://arxiv.org/abs/2112.12988 · HTML: https://mlsanity.com/paper/2112.12988/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 24 Dec 2021.

## Builds on (most cited first, 20 of 20)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans](https://mlsanity.com/paper/1812.07003/) (2018)
- [SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation](https://mlsanity.com/paper/1711.08588/) (2017)
- [Deep Interactive Object Selection](https://mlsanity.com/paper/1603.04042/) (2016)
- [GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud](https://mlsanity.com/paper/1812.03320/) (2018)
- [Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models](https://mlsanity.com/paper/1704.01222/) (2017)
- [f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation](https://mlsanity.com/paper/2001.10331/) (2020)
- [SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation](https://mlsanity.com/paper/1612.00606/) (2016)
- [3D Shape Segmentation with Projective Convolutional Networks](https://mlsanity.com/paper/1612.02808/) (2016)
- [Robust Watertight Manifold Surface Generation Method for ShapeNet Models](https://mlsanity.com/paper/1802.01698/) (2018)
- [StructureNet: Hierarchical Graph Networks for 3D Shape Generation](https://mlsanity.com/paper/1908.00575/) (2019)
- [Iteratively Trained Interactive Segmentation](https://mlsanity.com/paper/1805.04398/) (2018)
- [Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories](https://mlsanity.com/paper/2002.06478/) (2020)
- [3D Shape Segmentation via Shape Fully Convolutional Networks](https://mlsanity.com/paper/1702.08675/) (2017)
- [Predictive and Generative Neural Networks for Object Functionality](https://mlsanity.com/paper/2006.15520/) (2020)

## Built on by (most cited first, 1 of 1)

- [CloSe: A 3D Clothing Segmentation Dataset and Model](https://mlsanity.com/paper/2401.12051/) (2024)

## Abstract (arXiv)

A large-scale dataset is essential for learning good features in 3D shape understanding, but there are only a few datasets that can satisfy deep learning training. One of the major reasons is that current tools for annotating per-point semantic labels using polygons or scribbles are tedious and inefficient. To facilitate segmentation annotations in 3D shapes, we propose an effective annotation tool, named iSeg for 3D shape. It can obtain a satisfied segmentation result with minimal human clicks (< 10). Under our observation, most objects can be considered as the composition of finite primitive shapes, and we train iSeg3D model on our built primitive-composed shape data to learn the geometric prior knowledge in a self-supervised manner. Given human interactions, the learned knowledge can be used to segment parts on arbitrary shapes, in which positive clicks help associate the primitives into the semantic parts and negative clicks can avoid over-segmentation. Besides, We also provide an online human-in-loop fine-tuning module that enables the model perform better segmentation with less clicks. Experiments demonstrate the effectiveness of iSeg3D on PartNet shape segmentation. Data and codes will be made publicly available.