Timezone: »

DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis
Youngjoong Kwon · Lingjie Liu · Henry Fuchs · Marc Habermann · Christian Theobalt

Tue Dec 12 08:45 AM -- 10:45 AM (PST) @ Great Hall & Hall B1+B2 #2017
Event URL: https://vcai.mpi-inf.mpg.de/projects/DELIFFAS/ »

Generating controllable and photorealistic digital human avatars is a long-standing and important problem in Vision and Graphics. Recent methods have shown great progress in terms of either photorealism or inference speed while the combination of the two desired properties still remains unsolved. To this end, we propose a novel method, called DELIFFAS, which parameterizes the appearance of the human as a surface light field that is attached to a controllable and deforming human mesh model. At the core, we represent the light field around the human with a deformable two-surface parameterization, which enables fast and accurate inference of the human appearance. This allows perceptual supervision on the full image compared to previous approaches that could only supervise individual pixels or small patches due to their slow runtime. Our carefully designed human representation and supervision strategy leads to state-of-the-art synthesis results and inference time. The video results and code are available at https://vcai.mpi-inf.mpg.de/projects/DELIFFAS.

Author Information

Youngjoong Kwon (Robotics Institute, Carnegie Mellon University)
Lingjie Liu (University of Pennsylvania, University of Pennsylvania)
Henry Fuchs (Department of Computer Science, University of North Carolina, Chapel Hill)
Marc Habermann (Max Planck Institute for Informatics, Saarland Informatics Campus)

I am the research group leader of the Graphics and Vision for Digital Humans group at the Max Planck Institute for Informatics. My research interests lie in the field of Computer Vision, Computer Graphics, and Machine Learning. In particular, my work focuses on real-time human performance capture from single RGB videos, physical plausibility of the surface deformations and the human motion, photo-realistic animation synthesis, and learning generative 3D human characters from video. In summary, my research interests include (but are not limited to): Computer Vision, Computer Graphics, Machine Learning Human Performance Capture and Synthesis Reconstruction of Non-Rigid Deformations from RGB Video Neural Rendering Motion Capture

Christian Theobalt (MPI Informatik)

More from the Same Authors