no code implementations • 29 Feb 2024 • Lingchen Yang, Gaspard Zoss, Prashanth Chandran, Markus Gross, Barbara Solenthaler, Eftychios Sifakis, Derek Bradley
Physically-based simulation is a powerful approach for 3D facial animation as the resulting deformations are governed by physical constraints, allowing to easily resolve self-collisions, respond to external forces and perform realistic anatomy edits.
no code implementations • 27 Jan 2024 • Lingchen Yang, Gaspard Zoss, Prashanth Chandran, Paulo Gotardo, Markus Gross, Barbara Solenthaler, Eftychios Sifakis, Derek Bradley
At the core, we present a framework for learning implicit physics-based actuations for multiple subjects simultaneously, trained on a few arbitrary performance capture sequences from a small set of identities.
no code implementations • 12 Dec 2023 • Prashanth Chandran, Gaspard Zoss
Actor specific anatomically constrained face models are the state of the art in both facial performance capture and performance retargeting.
no code implementations • 6 Dec 2023 • Yingyan Xu, Prashanth Chandran, Sebastian Weiss, Markus Gross, Gaspard Zoss, Derek Bradley
An increasingly common approach for creating photo-realistic digital avatars is through the use of volumetric neural fields.
no code implementations • 30 Oct 2023 • Christopher Otto, Prashanth Chandran, Gaspard Zoss, Markus Gross, Paulo Gotardo, Derek Bradley
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 reconstruction given a particular image.
Ranked #7 on 3D Face Reconstruction on REALY (side-view)
no code implementations • CVPR 2023 • Prashanth Chandran, Gaspard Zoss, Paulo Gotardo, Derek Bradley
Neural networks for facial landmark detection are notoriously limited to a fixed set of landmarks in a dedicated layout, which must be specified at training time.
no code implementations • ICCV 2023 • Yingyan Xu, Gaspard Zoss, Prashanth Chandran, Markus Gross, Derek Bradley, Paulo Gotardo
Recent work on radiance fields and volumetric inverse rendering (e. g., NeRFs) has provided excellent results in building data-driven models of real scenes for novel view synthesis with high photorealism.
2 code implementations • CVPR 2021 • Prashanth Chandran, Gaspard Zoss, Paulo Gotardo, Markus Gross, Derek Bradley
Style transfer between images is an artistic application of CNNs, where the 'style' of one image is transferred onto another image while preserving the latter's content.
no code implementations • CVPR 2020 • Prashanth Chandran, Derek Bradley, Markus Gross, Thabo Beeler
Existing datasets used to train such algorithms are primarily made up of only low resolution images, and current algorithms are limited to inputs of comparable quality and resolution as the training dataset.