1
Decoupled rotation representation for category-level 6D pose estimation. This work is published in CVPR 2021.
In this work, we propose a novel pipeline, named FS-Net, for category-level 6D pose estimation. Our framework is built on our previous work G2L-Net, with the following Contributions:
-
New latent feature learning
»> 3D graph convolution based observed points reconstruction -
New rotation representation
»> Decomposable vector-based rotation representation -
New 3D data augmentation
»> Box-cage based, online 3D data augmentation
Due to our smart design, the proposed FS-Net runs at 20 FPS with state-of-the-art performance.
To give your project a background in the portfolio page, just add the img tag to the front matter like so:
---
layout: page
title: project
description: a project with a background image
img: /assets/img/12.jpg
---
You can also put regular text between your rows of images. Say you wanted to write a little bit about your project before you posted the rest of the images. You describe how you toiled, sweated, bled for your project, and then… you reveal it’s glory in the next row of images.
The code is simple.
Just wrap your images with <div class="col-sm"> and place them inside <div class="row"> (read more about the Bootstrap Grid system).
To make images responsive, add img-fluid class to each; for rounded corners and shadows use rounded and z-depth-1 classes.
Here’s the code for the last row of images above:
<div class="row justify-content-sm-center">
<div class="col-sm-8 mt-3 mt-md-0">
<img class="img-fluid rounded z-depth-1" src="/assets/img/6.jpg" alt="" title="example image"/>
</div>
<div class="col-sm-4 mt-3 mt-md-0">
<img class="img-fluid rounded z-depth-1" src="/assets/img/11.jpg" alt="" title="example image"/>
</div>
</div>