Litcius/Paper detail

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

Stavros Nousias, Gerasimos Arvanitis, Aris S. Lalos, Konstantinos Moustakas

2020IEEE Transactions on Industrial Informatics23 citationsDOIOpen Access PDF

Abstract

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 1e4 faces, the presented pipeline is twice as fast as methods with equivalent reconstruction error.

Topics & Concepts

Noise reductionComputer scienceArtificial intelligencePipeline (software)Face (sociological concept)Noise (video)Computer visionInferenceFilter (signal processing)CADPattern recognition (psychology)Image denoisingImage (mathematics)EngineeringSociologyProgramming languageSocial scienceEngineering drawing3D Surveying and Cultural Heritage3D Shape Modeling and AnalysisIndustrial Vision Systems and Defect Detection
Fast Mesh Denoising With Data Driven Normal Filtering Using Deep Variational Autoencoders | Litcius