SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

摘要:

We propose SDFDiff, a novel approach for image-based shape optimization using differentiable rendering of 3D  shapes represented by signed distance functions

and We apply our approach to the problem of multi-view 3D reconstruction,

SDF表示三维模型的优点: arbitrary topology,  guarantee watertight surfaces

简而言之:1、采用SDF表示三维模型 2、使用 3D differentiable rendering 来进行shape potimization