matthias.hernandez [at] gmail.com
3737 Watt Way PHE222
Los Angeles, CA 90089
Fall 2017: 3D Graphics and Rendering
Fall 2016: 3D Graphics and Rendering
Spring 2016: Artificial Intelligence
Fall 2015: 3D Graphics and Rendering
Spring 2015: Artificial Intelligence
Fall 2014: 3D Graphics and Rendering
M. Hernandez, T. Hassner, J. Choi and G. Medioni, "Accurate 3D Face Reconstruction via Prior Constrained Structure from Motion", Computer & Graphics 2017 [Article]
M. Hernandez, J. Choi and G. Medioni, "Near laser-scan quality 3-D face reconstruction from a low-quality depth stream", Image and Vision Computing, Apr. 2015 [PDF]
R. Wang*, M. Hernandez*, J. Choi and G. Medioni, "Accurate 3D Face and Body Modeling from a Single Fixed Kinect", IC3DST 2013 [PDF]
M. Hernandez, J. Choi and G. Medioni, "Laser scan quality 3-D face modeling using a low-cost depth camera", EUSIPCO 2012 [PDF]
M. Hernandez, G. Medioni, Z. Hu and S. Sadda, "Multimodal Registration of Multiple Retinal Images Based on Line Structures", WACV 2015 [PDF]
Z. Hu, G. Medioni, M. Hernandez and S. Sadda, "Automated segmentation of geographic atrophy in fundus autofluorescence images using supervised pixel classification", Journal of Medical Imaging, Jan. 2015 [Article]
Z. Hu, G. Medioni, M. Hernandez and S. Sadda, "Supervised Pixel Classification for Segmenting Geographic Atrophy in Fundus Autofluorescene Images", SPIE Medical Imaging, Mar. 2014 [Article]
Z. Hu, G. Medioni, M. Hernandez, A. Hariri, X. Wu and S. Sadda, "Segmentation of the Geographic Atrophy in Spectral-domain Optical Coherence Tomography Volume Scans and Fundus Autofluorescene Images", IOVS, Nov. 2013 [PDF]
3D FACE MODELING
We aim at reconstructing high-resolution 3D face models for unconstrained videos. We work with both RGB+D sensors and traditional cameras. Notably, we work with low-resolution videos that established technologies handle poorly.
3D FACE RECOGNITION
We aim at leveraging 3D data for face recognition tasks. We develop end-to-end deep learning methods for this purpose and study which factors impact recognition performance.
MULTIMODAL RETINAL IMAGE REGISTRATION
We aim at performing registration of retinal data across modalities and time automatically. This step is needed by ophthalmologists to formulate diagnosis and monitor disease evolution.
My research focuses on computer vision, computer graphics and machine learning. I address image registration and 3D reconstruction problems.
I work with many types of imagery, including medical 2D and OCT images, traditional cameras and RGB+D cameras.
Recently, I have taken interest in applying deep learning concepts to computer graphics.
I am a PhD candidate in Computer Science at USC. I work in the Institute for Robotics and Intelligent Systems, supervised by Prof. Gerard Medioni. In the past, I also collaborated with Dr. SriniVas Sadda at the Doheny Eye Institute UCLA.
I received my "diplome d'ingenieur" (MS) from the Paris Institute of Technology. My Master's thesis was supervised by Prof. Jean-Luc Dugelay at EURECOM and received the best Master's thesis award by the Mines-Télécom Foundation in 2012.
Find my resume here: [CV]