Jianfei Guo
 文章 标签 分类 关于
Jianfei Guo

目录

目录

收起 

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

Jianfei Guo 出版于 paper_reading
     约 78 字   预计阅读 1 分钟 
<DeepSDF> Deepsdf: Learning continuous signed distance functions for shape representation
 CVPR2019   Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, Steven Lovegrove
University of Washington, MIT    Faceboook reality labs
SDF
Cite Preprint Code

Motivation

  • SDF是CG领域又一个形状的表征；本篇是first to use deep SDF functions to model shapes
  • https://longtimenohack.com/posts/paper_reading/2019cvpr_park_deepsdf/image-20201210100006815.png
  • https://longtimenohack.com/posts/paper_reading/2019cvpr_park_deepsdf/image-20201210095931233.png

overview

  • 单个形状用单个SDF网络，一个category用code conditioned
    https://longtimenohack.com/posts/paper_reading/2019cvpr_park_deepsdf/image-20201210100154456.png
  • 使用auto-decoder
    https://longtimenohack.com/posts/paper_reading/2019cvpr_park_deepsdf/image-20201210100244493.png
更新于 2020-12-03
阅读原始文档