“Textured Mesh Quality Assessment: Large-scale Dataset and Deep Learning-based Quality Metric” by Nehmé, Delanoy, Dupont, Farrugia and Le Callet

  • ©Yana Nehmé, Johanna Delanoy, Florent Dupont, Jean-Philippe Farrugia, and Patrick Le Callet

Conference:


Type(s):


Title:

    Textured Mesh Quality Assessment: Large-scale Dataset and Deep Learning-based Quality Metric

Session/Category Title:   Material Rendering


Presenter(s)/Author(s):


Moderator(s):



Abstract:


    We present a dataset and metric for the visual quality assessment of textured meshes. The dataset contains 343K distorted meshes of which 3,000 have been subjectively rated in a crowdsourcing study. Leveraging this dataset, we propose a learning-based perceptual metric able to predict the perceived visual quality.


ACM Digital Library Publication:



Overview Page: