My research aims at understanding the world through the capture and analysis of heterogeneous data, in order to create applied digital instruments.
Examples of heterogeneous data are optical images obtained with visible light cameras,
medical images obtained with Magnetic Resonance Imaging (MRI) or Computed Tomography (CT) scanners,as well as geometry data obtained with depth sensors.
Examples of digital instruments are tools that allow
to generate novel views from a scene,
to infer the human shape from a clothed scan,
or to predict the amount of adipose tissue of a person from surface observations.
To address this challenge, I adopt the approaches of Computer Vision, Signal Processing, Computer Graphics and Statistical Models.
My research is often multi-disciplinary, as I need to combine knowledge from these different domains.
The instruments resulting from my research allow practitioners to create new digital representations of the world, and help them to interact with it.
I have collaborated with practitioners, like cinema directors, artists and doctors.
In addition to scientific publications, transfer to the industry is a significant result of my research.
Prior to research, I have an extensive (7 years) experience in the industry
that allowed me to understand professional
needs while closely collaborating with the academic community.
capture and analysis of heterogeneous data applied digital instruments digital representations of the world statistical models
In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017, Spotlight (inproceedings)
We address the problem of estimating human body shape from 3D scans over time. Reliable estimation of 3D body shape is necessary for many applications including virtual try-on, health monitoring, and avatar creation for virtual reality. Scanning bodies in minimal clothing, however, presents a practical barrier to these applications. We address this problem by estimating body shape under clothing from a sequence of 3D scans. Previous methods that have exploited statistical models of body shape produce overly smooth shapes lacking personalized details. In this paper we contribute a new approach to recover not only an approximate shape of the person, but also their detailed shape. Our approach allows the estimated shape to deviate from a parametric model to fit the 3D scans. We demonstrate the method using high quality 4D data as well as sequences of visual hulls extracted from multi-view images. We also make available a new high quality 4D dataset that enables quantitative evaluation. Our method outperforms the previous state of the art, both qualitatively and quantitatively.
ACM Transactions on Graphics, (Proc. SIGGRAPH), 36(4), 2017 (article)
Data driven models of human poses and soft-tissue deformations can produce very realistic results, but they only model the visible surface of the human body and cannot create skin deformation due to interactions with the environment. Physical simulations can generalize to external forces, but their parameters are difficult to control. In this paper, we present a layered volumetric human body model learned from data. Our model is composed of a data-driven inner layer and a physics-based external layer. The inner layer is driven with a volumetric statistical body model (VSMPL). The soft tissue layer consists of a tetrahedral mesh that is driven using the finite element method (FEM). Model parameters, namely the segmentation of the body into layers and the soft tissue elasticity, are learned directly from 4D registrations of humans exhibiting soft tissue deformations. The learned two layer model is a realistic full-body avatar that generalizes to novel motions and external forces. Experiments show that the resulting avatars produce realistic results on held out sequences and react to external forces. Moreover, the model supports the retargeting of physical properties from one avatar when they share the same topology.
ACM Transactions on Graphics, (Proc. SIGGRAPH), 36(4), 2017, Two first authors contributed equally (article)
Designing and simulating realistic clothing is challenging and, while several methods have addressed the capture of clothing from 3D scans, previous methods have been limited to single garments and simple motions, lack detail, or require specialized texture patterns. Here we address the problem of capturing regular clothing on fully dressed people in motion. People typically wear multiple pieces of clothing at a time. To estimate the shape of such clothing, track it over time, and render it believably, each garment must be segmented from the others and the body. Our ClothCap approach uses a new multi-part 3D model of clothed bodies, automatically segments each piece of clothing, estimates the naked body shape and pose under the clothing, and tracks the 3D deformations of the clothing over time. We estimate the garments and their motion from 4D scans; that is, high-resolution 3D scans of the subject in motion at 60 fps. The model allows us to capture a clothed person in motion, extract their clothing, and retarget the clothing to new body shapes. ClothCap provides a step towards virtual try-on with a technology for capturing, modeling, and analyzing clothing in motion.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems