Zhiqi Kang

Zhiqi Kang
National Institute for Research in Computer Science and Control | INRIA · PERCEPTION - Interpretation and Modelling of Images and Videos Research Team

About

5
Publications
91
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4
Citations

Publications

Publications (5)
Preprint
Full-text available
Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a frontalization methodology that preserves non-rigid facial deformations in order to boost the performance of visually assisted speech communication. The method alternates between the estimation of (i)~the rig...
Preprint
This paper investigates the impact of head movements on audio-visual speech enhancement (AVSE). Although being a common conversational feature, head movements have been ignored by past and recent studies: they challenge today's learning-based methods as they often degrade the performance of models that are trained on clean, frontal, and steady face...
Preprint
Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a robust face alignment method that enables pixel-to-pixel warping. The method simultaneously estimates the \textit{rigid transformation} (scale, rotation, and translation) and the \textit{non-rigid deformation...

Network