Presentation / Installation


Textured Mesh Quality Assessment: Large-scale Dataset and Deep Learning-based Quality Metric
SessionMaterial Rendering
DescriptionWe 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.
Authors
Yana Nehmé
TechViz
Johanna Delanoy
Université de Lyon, INSA Lyon, CNRS, LIRIS
Florent Dupont
Université de Lyon, Université Lyon 1, CNRS, LIRIS
Jean-Philippe Farrugia
Université de Lyon, Université Lyon 1, CNRS, LIRIS
Patrick Le Callet
Nantes Université, Ecole Centrale Nantes, CNRS, LS2N
Guillaume Lavoué
Université de Lyon, Centrale Lyon, ENISE, CNRS, LIRIS
Presenter
Yana Nehmé
TechViz
Event Type
Technical Paper
TimeWednesday, 9 August 20232:22pm - 2:33pm PDT
LocationPetree Hall D
ACM Digital Library Technical Papers pdfs
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Wednesday, 9 August 20232pm - 3:30pm PDTPetree Hall D
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Rendering
Video
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
NeuSample: Importance Sampling for Neural Materials