We present a new method for the robust transfer of skin weights from a source mesh to a target mesh with significantly different geometric shapes. Rigging garments is a typical application of skin weight transfer where weights are copied from a source body mesh to avoid tedious weight painting from scratch. However, existing techniques struggle with non-skin-tight garments and require additional manual weight painting. We introduce a fully automatic two-stage skin weight transfer process. First, an initial transfer is performed by copying weights from the source mesh only for those vertices on the target mesh where we have high confidence in obtaining the ground truth weights from the source. Then, we automatically compute weights for all other vertices by interpolating the weights computed in stage one. This approach is robust and easy to implement in practice, yet it far outperforms the methods used in existing commercial software and previous research works
@inproceedings{abdrashitov2023robust,
author = {Abdrashitov, Rinat and Raichstat, Kim and Monsen, Jared and Hill, David},
title = {Robust Skin Weights Transfer via Weight Inpainting},
year = {2023},
isbn = {9798400703140},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3610543.3626180},
doi = {10.1145/3610543.3626180},
booktitle = {SIGGRAPH Asia 2023 Technical Communications},
articleno = {25},
numpages = {4},
location = {<conf-loc>, <city>Sydney</city>, <state>NSW</state>, <country>Australia</country>, </conf-loc>},
series = {SA '23}
}
We express our gratitude to the Geometry Team members: Tyson Brochu, Jimmy Andrews, Ryan Schmidt and the Cloth Team members: Kriss Gossart, Alex McAdams, Tim Brakensiek, Michael Lentine, for their valuable advice and guidance.