未加星标

Ask HN: Data augmentation tools for 3d object detection

字体大小 | |
[前端(javascript) 所属分类 前端(javascript) | 发布者 店小二05 | 时间 2018 | 作者 红领巾 ] 0人收藏点击收藏

Are you talking about a depth channel on an image plane? It also largely depend on the problem but here is a few tricks that helped me for my problems (object tracking).

- Generating synthetic data is powerful if you have the depth modality as it is easy to render. Also the real/synthetic domain gap is narrow compared to RGB. I consider it as data augmentation: you usually do many renders from a single 3D model.

- If you can somehow normalize the offset (e.g. compute normals) that can help. In my case I could offset the center of the object as 0 depth and it greatly help the network to converge.

- Classic augmentations like gaussian noise, gaussian blur and also downsampling the depth helps (apply these randomly).

As for tooling, I just use numpy/pytorch for most operations and OpenGL for renders.

本文前端(javascript)相关术语:javascript是什么意思 javascript下载 javascript权威指南 javascript基础教程 javascript 正则表达式 javascript设计模式 javascript高级程序设计 精通javascript javascript教程

分页:12
转载请注明
本文标题:Ask HN: Data augmentation tools for 3d object detection
本站链接:https://www.codesec.net/view/620806.html


1.凡CodeSecTeam转载的文章,均出自其它媒体或其他官网介绍,目的在于传递更多的信息,并不代表本站赞同其观点和其真实性负责;
2.转载的文章仅代表原创作者观点,与本站无关。其原创性以及文中陈述文字和内容未经本站证实,本站对该文以及其中全部或者部分内容、文字的真实性、完整性、及时性,不作出任何保证或承若;
3.如本站转载稿涉及版权等问题,请作者及时联系本站,我们会及时处理。
登录后可拥有收藏文章、关注作者等权限...
技术大类 技术大类 | 前端(javascript) | 评论(0) | 阅读(11)