We present a novel self-supervised framework for learning the discretization-agnostic surface parameterization of arbitrary 3D objects with both open and closed surfaces. Our framework leverages diffusion-enabled global-to-local shape context for each vertex first to partition the closed surface into multiple patches using the proposed self-supervised PatchNet and subsequently perform independent UV parameterization of these patches by learning forward and backward UV mapping for individual patches. Thus, our framework enables learning a discretization-agnostic parameterization at a lower resolution and then directly inferring the parameterization for a higher-resolution mesh without retraining. We evaluate our framework on multiple 3D objects from the publicly available SHREC dataset and report superior/faster UV parameterization over conventional methods.
@inproceedings{10.1145/3550340.3564235,
author = {Pokhariya, Chandradeep and Naik, Shanthika and Srivastava, Astitva and Sharma, Avinash},
title = {Discretization-Agnostic Deep Self-Supervised 3D Surface Parameterization},
year = {2022},
isbn = {9781450394659},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3550340.3564235},
doi = {10.1145/3550340.3564235},
booktitle = {SIGGRAPH Asia 2022 Technical Communications},
articleno = {2},
numpages = {4},
keywords = {UV parameterization, self-supervised learning, texture mapping, neural network, surface parameterization.},
location = {Daegu, Republic of Korea},
series = {SA '22}
}