# Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning

Source: [Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning](<https://www.sota2.com/research/paper/68fa67ec1e209131cea1929e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:25:00.051Z

Authors: Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim

Published: 2020-07-07T02:17:44.000Z

## Abstract

We propose spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning. The raw 3D reconstruction of an indoor environment suffers from occlusions, noise, and is produced without any meaningful distinction between individual entities. For high-level intelligent tasks from a large scale scene, 3D instance segmentation recognizes individual instances of objects. We approach the instance segmentation by simply learning the correct embedding space that maps individual instances of objects into distinct clusters that reflect both spatial and semantic information. Unlike previous approaches that require complex pre-processing or post-processing, our implementation is compact and fast with competitive performance, maintaining scalability on large scenes with high resolution voxels. We demonstrate the state-of-the-art performance of our algorithm in the ScanNet 3D instance segmentation benchmark on AP score.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Instance Segmentation on ScanNet v2 (test)](<https://www.sota2.com/research/sota/3d-instance-segmentation-on-scannet-v2-test.md>): 3D Instance Segmentation; ScanNet v2 (test); mAP: 38.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.03169>)

[PDF](<https://arxiv.org/pdf/2007.03169.pdf>)
