目录

目录

Semi-Supervised Learning of Multi-Object 3D Scene Representations


Semi-supervised learning of multi-object 3D scene representations

Review

  • 只用了clevrn类数据集,而且甚至还是简单的低分辨率渲染,实验比较简单

Motivation

  • 把场景表征为多个物体
  • 输入input RGB image,通过一个recurrent encoder,回归出每个物体的shape, pose, texture;shape通过SDF表征
  • 半监督体现在训练时候用的是RGB-D,测试时候只需要RGB
  • single view见所有物体;物体个数是已知的
    https://longtimenohack.com/posts/paper_reading/2020arxiv_elich_semi/image-20201222094044348.png

Overview

  • 首先从example shapes有监督地训练SDF(的decoder);
  • 然后自监督地通过RGB-D训练differentiable renderer和recurrent encoder
  • Q: recurrent真的能这样设计吗?
    https://longtimenohack.com/posts/paper_reading/2020arxiv_elich_semi/image-20201222090334334.png
  • 可以看到recurrent的主要目的是迭代、逐个地得出object的code,倒是和之前*Multi-object representation learning with iterative variational inference.*那篇有些像
    每个物体输出深度估计,图像估计,与occulusion mask
    https://longtimenohack.com/posts/paper_reading/2020arxiv_elich_semi/image-20201222091509810.png

results

  • https://longtimenohack.com/posts/paper_reading/2020arxiv_elich_semi/image-20201222090527412.png