目录

目录

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction


<DISN> DISN: Deep implicit surface network for high-quality single-view 3D reconstruction

review

  • 训练时是有3D shape 的SDF的真值数据的;图像feature只是提供一个辅助的code输入而已

Motivation

  • 希望学到的shape,不仅全局特征好,还想有局部fine grained details 细粒度细节

overview

  • 同时用global features和local features来infer SDF
    https://longtimenohack.com/posts/paper_reading/2019nips_xu_disn/image-20201209122023941.png