Some leading advances of the Ageing@Work project were presented in the IEEE International Conference on Industrial Informatics (INDIN’19) in Helsinki through the paper titled “Fast mesh denoising with data driven normal filtering using deep autoencoders”.
In this paper, UPAT, a major partner of the Ageing@Work project, propose a fast and reliable denoising method that can be effectively applied for reconstructing very dense noisy 3D models. The proposed method applies conditional variational autoencoders on face normals. Extensive evaluation studies carried out using a variety of 3D models verify that the proposed approach achieves plausible reconstruction outputs, very relative or even better of those proposed by the literature, in considerably faster execution times.
More information about the paper can be found here.