Geometry Denoising with Preferred Normal Vectors

TL;DR

This paper presents a novel geometry denoising method leveraging prior knowledge of preferred surface normal vectors, integrating segmentation and regularization within an optimization framework to improve surface reconstruction accuracy.

Contribution

It introduces a new geometry denoising paradigm using label vectors for normals, combining segmentation and total variation regularization with a split Bregman approach.

Findings

Effective denoising with normal vector priors

Integration of segmentation into the denoising process

Use of split Bregman method for optimization

Abstract

We introduce a new paradigm for geometry denoising using prior knowledge about the surface normal vector. This prior knowledge comes in the form of a set of preferred normal vectors, which we refer to as label vectors. A segmentation problem is naturally embedded in the denoising process. The segmentation is based on the similarity of the normal vector to the elements of the set of label vectors. Regularization is achieved by a total variation term. We formulate a split Bregman (ADMM) approach to solve the resulting optimization problem. The vertex update step is based on second-order shape calculus.