Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performances

Paul Knoll, Paul Knoll, Wieland Morgenstern, Anna Hilsmann, Anna Hilsmann, Peter Eisert, Peter Eisert

2024

Abstract

Creating high-quality controllable 3D human models from multi-view RGB videos poses a significant challenge. Neural radiance fields (NeRFs) have demonstrated remarkable quality in reconstructing and free-viewpoint rendering of static as well as dynamic scenes. The extension to a controllable synthesis of dynamic human performances poses an exciting research question. In this paper, we introduce a novel NeRF-based framework for pose-dependent rendering of human performances. In our approach, the radiance field is warped around an SMPL body mesh, thereby creating a new surface-aligned representation. Our representation can be animated through skeletal joint parameters that are provided to the NeRF in addition to the viewpoint for pose dependent appearances. To achieve this, our representation includes the corresponding 2D UV coordinates on the mesh texture map and the distance between the query point and the mesh. To enable efficient learning despite mapping ambiguities and random visual variations, we introduce a novel remapping process that refines the mapped coordinates. Experiments demonstrate that our approach results in high-quality renderings for novel-view and novel-pose synthesis.

Paper Citation

in Harvard Style

Knoll P., Morgenstern W., Hilsmann A. and Eisert P. (2024). Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performances. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 404-413. DOI: 10.5220/0012373800003660

in Bibtex Style

@conference{visapp24,
author={Paul Knoll and Wieland Morgenstern and Anna Hilsmann and Peter Eisert},
title={Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performances},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP},
year={2024},
pages={404-413},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012373800003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP
TI - Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performances
SN - 978-989-758-679-8
AU - Knoll P.
AU - Morgenstern W.
AU - Hilsmann A.
AU - Eisert P.
PY - 2024
SP - 404
EP - 413
DO - 10.5220/0012373800003660
PB - SciTePress