Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields
Abstract
We present implicit displacement fields, a novel representation for detailed 3D geometry. Inspired by a classic surface deformation technique, displacement mapping, our method represents a complex surface as a smooth base surface plus a displacement along the base's normal directions, resulting in a frequency-based shape decomposition, where the high-frequency signal is constrained geometrically by the low-frequency signal. Importantly, this disentanglement is unsupervised thanks to a tailored architectural design that has an innate frequency hierarchy by construction. We explore implicit displacement field surface reconstruction and detail transfer and demonstrate superior representational power, training stability, and generalizability.
Cite
Text
Yifan et al. "Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields." International Conference on Learning Representations, 2022.Markdown
[Yifan et al. "Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields." International Conference on Learning Representations, 2022.](https://mlanthology.org/iclr/2022/yifan2022iclr-geometryconsistent/)BibTeX
@inproceedings{yifan2022iclr-geometryconsistent,
title = {{Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields}},
author = {Yifan, Wang and Rahmann, Lukas and Sorkine-hornung, Olga},
booktitle = {International Conference on Learning Representations},
year = {2022},
url = {https://mlanthology.org/iclr/2022/yifan2022iclr-geometryconsistent/}
}