# 3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

arXiv: https://arxiv.org/abs/2003.00535 · HTML: https://mlsanity.com/paper/2003.00535/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2020.

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

- [Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16470/) (2021)
- [The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection](https://mlsanity.com/paper/2112.14023/) (2021)
- [AGO-Net: Association-Guided 3D Point Cloud Object Detection Network](https://mlsanity.com/paper/2208.11658/) (2022)
- [Object-based SLAM utilizing unambiguous pose parameters considering general symmetry types](https://mlsanity.com/paper/2303.07872/) (2023)

## Abstract (arXiv)

We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptively selects and fuses the reciprocal semantic and instance features from two tasks in a coupled manner. To further boost the performance of the instance segmentation task in our 3DCFS, we investigate a loss function that helps the model learn to balance the magnitudes of the output embedding dimensions during training, which makes calculating the Euclidean distance more reliable and enhances the generalizability of the model. Extensive experiments demonstrate that our 3DCFS outperforms state-of-the-art methods on benchmark datasets in terms of accuracy, speed and computational cost.