Fast mesh denoising with data driven normal filtering using deep variational autoencoders

TL;DR

This paper introduces a fast, data-driven normal filtering method for denoising dense 3D scanned models using deep variational autoencoders, achieving high accuracy and efficiency in industrial applications.

Contribution

It presents a novel denoising approach employing conditional variational autoencoders with a sliding patch setup, reducing training data and inference time while maintaining high reconstruction quality.

Findings

Achieves denoising with similar or higher accuracy than state-of-the-art methods.

For models with over 10,000 faces, it is twice as fast as comparable approaches.

Demonstrates robustness and efficiency on real 3D scanned and CAD models.

Abstract

Recent advances in 3D scanning technology have enabled the deployment of 3D models in various industrial applications like digital twins, remote inspection and reverse engineering. Despite their evolving performance, 3D scanners, still introduce noise and artifacts in the acquired dense models. In this work, we propose a fast and robust denoising method for dense 3D scanned industrial models. The proposed approach employs conditional variational autoencoders to effectively filter face normals. Training and inference are performed in a sliding patch setup reducing the size of the required training data and execution times. We conducted extensive evaluation studies using 3D scanned and CAD models. The results verify plausible denoising outcomes, demonstrating similar or higher reconstruction accuracy, compared to other state-of-the-art approaches. Specifically, for 3D models with more than 1e4 faces, the presented pipeline is twice as fast as methods with equivalent reconstruction error.