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

2020-07-07 · Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim

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.

📄 PDF Abstract BibTeX arXiv:2007.03169

Code (1)

96lives/ssen 공식 구현 pytorch

Tasks

3D Instance Segmentation 3D Reconstruction Instance Segmentation Metric Learning Segmentation Semantic Segmentation

Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

2019-06-26 · CVPR 2019 6 · Davy Neven, Bert de Brabandere, Marc Proesmans, Luc van Gool

Current state-of-the-art instance segmentation methods are not suited for real-time applications like autonomous driving, which require fast execution times at high accuracy. Although the currently dominant proposal-base…

Autonomous Driving Clustering Instance Segmentation Segmentation+1

PanoNet: Real-time Panoptic Segmentation through Position-Sensitive Feature Embedding

2020-08-01 · Xia Chen, Jianren Wang, Martial Hebert

We propose a simple, fast, and flexible framework to generate simultaneously semantic and instance masks for panoptic segmentation. Our method, called PanoNet, incorporates a clean and natural structure design that tackl…

Autonomous Driving Panoptic Segmentation Position Segmentation

Spatial Sampling Network for Fast Scene Understanding

2019-05-22 · Davide Mazzini, Raimondo Schettini

We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common s…

Decoder Instance Segmentation Scene Understanding Segmentation+1

Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation

2020-09-28 · Naiyu Gao, Yanhu Shan, Xin Zhao, Kaiqi Huang

Panoptic segmentation (PS) is a complex scene understanding task that requires providing high-quality segmentation for both thing objects and stuff regions. Previous methods handle these two classes with semantic and ins…

Instance Segmentation Panoptic Segmentation Scene Understanding Segmentation+1

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

2020-03-01 · Liang Du, Jingang Tan, xiangyang xue, Lili Chen 외

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 proce…

3D Semantic Instance Segmentation feature selection Instance Segmentation Segmentation+1