Geometric and Learning-based Mesh Denoising: A Comprehensive Survey

TL;DR

This survey comprehensively reviews traditional and learning-based mesh denoising methods, analyzing their categories, effectiveness, and future directions, supported by a benchmark for evaluation.

Contribution

It provides the first extensive comparison and categorization of mesh denoising techniques, including a new benchmark for evaluation.

Findings

Learning-based methods show promising generalization.

Optimization and filter methods remain effective.

Benchmark facilitates fair comparison of denoising approaches.

Abstract

Mesh denoising is a fundamental problem in digital geometry processing. It seeks to remove surface noise, while preserving surface intrinsic signals as accurately as possible. While the traditional wisdom has been built upon specialized priors to smooth surfaces, learning-based approaches are making their debut with great success in generalization and automation. In this work, we provide a comprehensive review of the advances in mesh denoising, containing both traditional geometric approaches and recent learning-based methods. First, to familiarize readers with the denoising tasks, we summarize four common issues in mesh denoising. We then provide two categorizations of the existing denoising methods. Furthermore, three important categories, including optimization-, filter-, and data-driven-based techniques, are introduced and analyzed in detail, respectively. Both qualitative and quantitative comparisons are illustrated, to demonstrate the effectiveness of the state-of-the-art denoising methods. Finally, potential directions of future work are pointed out to solve the common problems of these approaches. A mesh denoising benchmark is also built in this work, and future researchers will easily and conveniently evaluate their methods with the state-of-the-art approaches.