Gaspard Zoss

Gaspard Zoss

Research Scientist

DisneyResearch|Studios

I’m a Research Scientist with the Digital Humans group at DisneyResearch|Studios. I received a Bachelor and Master of Communication Systems from EPFL in 2016 and 2018 respectively and did a PhD in Computer Science at ETH Zurich jointly with DisneyResearch|Studios. My research interests lie at the intersection of computer graphics, computer vision and machine learning with a particular focus on methods to capture, reconstruct and animate human faces with the goal of creating high quality digital humans for VFX and entertainment.

Interests

  • Digital Humans
  • Performance Capture
  • Data-Driven Methods

Education

  • PhD in Computer Vision/Graphics, 2021

    ETH Zurich and DisneyResearch|Studios

  • Master in Communication Systems, 2018

    École Polytechnique Fédérale de Lausanne

  • Bachelor in Communication Systems, 2016

    École Polytechnique Fédérale de Lausanne

Publications

In this paper, we target the application scenario of capturing high-fidelity assets for neural relighting in controlled studio …

In this work, we propose a new loss function for monocular face capture, inspired by how humans would perceive the quality of a 3D face …

We present a novel graph-based simulation approach for generating micro wrinkle geometry on human skin, which can easily scale up to …

We propose the first facial landmark detection network that can predict continuous, unlimited landmarks, allowing to specify the number …

We demonstrate how the simple U-Net, surprisingly, allows us to advance the state of the art for re-aging real faces on video, with …

We approach the problem of face swapping from the perspective of learning simultaneous convolutional facial autoencoders for the source …

We propose a 3D+time framework for modeling dynamic sequences of 3D facial shapes, representing realistic non-rigid motion during a …

We demonstrate the proposed capture pipeline on a variety of different facial hair styles and lengths, ranging from sparse and short to …

We apply the method to volumetric soft bodies, human poses, and facial expressions, demonstrating artist-friendly properties.

We demonstrate how MoRF is a strong new step towards 3D morphable neural head modeling.

We present a new nonlinear parametric 3D shape model based on transformer architectures.

We compare the results obtained with a state-of-the-art appearance capture method [RGB∗20], with and without our proposed improvements …

We propose to combine incomplete, high-quality renderings showing only facial skin with recent methods for neural rendering of faces, …

We propose Adaptive convolutions; a generic extension of AdaIN, which allows for the simultaneous transfer of both statistical and …

Our work aims to compute and characterize the difference between the captured dynamic facial performance, and a speculative quasistatic …

We propose a novel interactive method for the creation of digital faces that is simple and intuitive to use, even for novice users, …

We introduce a novel iterative solver for nonlinear least squares optimization of large-scale semi-sparse problems suitable to be …

We present the first method to accurately track the invisible jaw based solely on the visible skin surface, without the need for any …

We present a new jaw rig, empirically designed from accurate capture data, and we provide a simple method to retarget the rig to new …

Contact

  • gaspard.zoss at disneyresearch.com
  • +41 44 632 28 37
  • DisneyResearch|Studios
    Stampfenbachstrasse 48, Zurich, 8006