Fast Mesh Denoising With Data Driven Normal Filtering Using Deep Variational Autoencoders

• Published in: IEEE transactions on industrial informatics 2021-02, Vol.17 (2), p.980-990
• Main Authors: Nousias, Stavros, Arvanitis, Gerasimos, Lalos, Aris S., Moustakas, Konstantinos
• Format: Article
• Language: English
• Subjects: 3-D mesh denoising; data driven normal filtering; Decoding; Face; Finite element method; Image reconstruction; Industrial applications; Inspection; Noise reduction; Reverse engineering; Scanners; Solid modeling; Tensors; Three dimensional models; Three-dimensional displays; Training; variational autoencoders
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2020.3000491

Recent advances in 3-D scanning technology have enabled the deployment of 3-D models in various industrial applications such as digital twins, remote inspection, and reverse engineering. Despite their evolving performance, 3-D scanners still introduce noise and artifacts in the acquired dense models. In this article, we propose a fast and robust denoising method for the dense 3-D 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 3-D 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 3-D models with more than 1\text{e}4 faces, the presented pipeline is twice as fast as methods with equivalent reconstruction error.