VLG | Computer Vision and Learning Group

Basic Information

I am a Ph.D. student with the Max Planck ETH Center for Learning Systems (CLS), supervised by Siyu Tang (ETH), Justus Thies (MPI-IS, Tübingen & TU Darmstadt), and Otmar Hilliges (ETH). My research focuses on reconstructing photo-realistic 3D avatars of the human head with affordable capturing hardware with a particular emphasis on extreme expressions. Such technology will be a crucial step towards next-gen telecommunication and entertainment, e.g., in immersive 3D video-conferencing and VR gaming.

Social

Publications

DINER: Depth-aware Image-based Neural Radiance Fields

Conference: Conference on Computer Vision and Pattern Recognition (CVPR 2023)

Authors:Malte Prinzler, Otmar Hilliges, Justus Thies
Few-view NeRF Reconstructions exploiting Depth-Priors.

Project PDF Code BibTeX

Neural Head Avatars from Monocular RGB Videos

Conference: Conference on Computer Vision and Pattern Recognition (CVPR 2022)

Authors:Philip-William Grassal, Malte Prinzler, Titus Leistner, Carsten Rother, Matthias Nießner, Justus Thies (*equal contribution)
Reconstructing controllable, photo-realistic 3D head avatars from monocular RGB videos.

Project PDF Code BibTeX

MATCH: Feed-forward Gaussian Registration for Head Avatar Creation and Editing

Conference: Conference on Computer Vision and Pattern Recognition (CVPR 2026)

Authors:Malte Prinzler, Paulo Gotardo, Siyu Tang, Timo Bolkart
Given calibrated multi-view images of human heads, MATCH infers static Gaussian splat textures in dense semantic correspondence.

Project PDF Code BibTeX

Basic Information

Social

Publications

DINER: Depth-aware Image-based Neural Radiance Fields

Authors:Malte Prinzler, Otmar Hilliges, Justus Thies Few-view NeRF Reconstructions exploiting Depth-Priors.

Neural Head Avatars from Monocular RGB Videos

Authors:Philip-William Grassal*, Malte Prinzler*, Titus Leistner, Carsten Rother, Matthias Nießner, Justus Thies (*equal contribution) Reconstructing controllable, photo-realistic 3D head avatars from monocular RGB videos.

MATCH: Feed-forward Gaussian Registration for Head Avatar Creation and Editing

Authors:Malte Prinzler, Paulo Gotardo, Siyu Tang, Timo Bolkart Given calibrated multi-view images of human heads, MATCH infers static Gaussian splat textures in dense semantic correspondence.

Authors:Malte Prinzler, Otmar Hilliges, Justus Thies
Few-view NeRF Reconstructions exploiting Depth-Priors.

Authors:Philip-William Grassal, Malte Prinzler, Titus Leistner, Carsten Rother, Matthias Nießner, Justus Thies (*equal contribution)
Reconstructing controllable, photo-realistic 3D head avatars from monocular RGB videos.

Authors:Malte Prinzler, Paulo Gotardo, Siyu Tang, Timo Bolkart
Given calibrated multi-view images of human heads, MATCH infers static Gaussian splat textures in dense semantic correspondence.