0
点赞
收藏
分享

微信扫一扫

2020-3D Semantic Segmentation for Large-Scale Scene


3D Semantic Segmentation for Large-Scale Scene Understanding

Kiran Akadas and Shankar Gangisetty
KLE Technological University, Hubballi, India
akadask@gmail.com, shankar@kletech.ac.in

年份:2020

期刊/会议:ACCV

代码:https://github.com/KiranAkadas/GRanDNet

1、创新

  • 基于RandLA-net,随机采样,速度快、效率高
  • 使用了空洞卷积
  • GeLU作为激活函数,对拟合方程更有帮助
  • 提出了可选的CRF优化方法

2、具体实现

2020-3D Semantic Segmentation for Large-Scale Scene_激活函数

3、实验结果

SHREC 2020

2020-3D Semantic Segmentation for Large-Scale Scene_pointcloud_02

2020-3D Semantic Segmentation for Large-Scale Scene_github_03

2020-3D Semantic Segmentation for Large-Scale Scene_激活函数_04

S3DIS

2020-3D Semantic Segmentation for Large-Scale Scene_github_05

2020-3D Semantic Segmentation for Large-Scale Scene_github_06

SemanticKITTI

2020-3D Semantic Segmentation for Large-Scale Scene_github_07

2020-3D Semantic Segmentation for Large-Scale Scene_github_08


举报

相关推荐

0 条评论