The aim of this Master 2 internship is to study Video Quality Assessment (VQA) algorithms adapted directly into the compressed domain taking into account the variability of codecs and the specificity of video coding. Yet, instead of scoring the quality of video by a single value, a continuous notation of the quality will be preferred. The problem of perceptual video quality assessment is a significantly more complex problem than the still image one for the following reason: while there exist highly reliable models of still natural scene statistics, the literature for regular natural video statistics models is almost absent. For instance, the interaction between motion and spatio-temporal changes is of particular interest, especially with regards to whether motion is involved in masking distortions. The type of motion which occurs in a video is a function of object and camera movements. One challenge is how the aforementioned phenomenon can be modeled into the compressed domain?
The candidate will investigate how the design of existing relevant features in the wavelet domain, frequency domain and/or spatial domain, or temporal domain could be adapted in the compressed domain.
The use of Deep Learning to design such a VQA scheme could be investigated too.
Applications should include the following:
Alexandre Ninassi (email@example.com)
Christophe Charrier (firstname.lastname@example.org)
(c) GdR 720 ISIS - CNRS - 2011-2018.