Mesh Saliency Detection Using Convolutional Neural Networks

This resource contains the presentation of the paper entitled "Mesh Saliency Detection Using Convolutional Neural Network" with DOI 10.1109/ICME46284.2020.9102796 that took place in 2020 IEEE International Conference on Multimedia and Expo (ICME).

The paper is proposing the use of convolutional neural networks to extract mesh saliency, a visual metric that has been widely considered as the measure of visual importance of certain parts of 3D geometries. Salient parts are distinguishable from their surroundings, with respect to human visual perception. 

The proposed architecture is trained with saliency maps constructed with a fusion spectral and geometrical analysis generated measures. Extensive evaluation studies carried out, include visual perception evaluation, simplification and compression use cases.

As a result, they verify the superiority of our approach as compared to other state-of-theart approaches. Furthermore, performance experiments indicate that CNN-based saliency extraction method is much faster in large and dense geometries allowing its application in low-latency and energy-efficient systems