Timezone: »
We introduce an approach for establishing dense correspondences between partial scans of human models and a complete template model. Our approach's key novelty lies in formulating dense correspondence computation as initializing and synchronizing local transformations between the scan and the template model. We introduce an optimization formulation for synchronizing transformations among a graph of the input scan, which automatically enforces smoothness of correspondences and recovers the underlying articulated deformations. We then show how to convert the iterative optimization procedure among a graph of the input scan into an end-to-end trainable network. The network design utilizes additional trainable parameters to break the barrier of the original optimization formulation's exact and robust recovery conditions. Experimental results on benchmark datasets demonstrate that our approach considerably outperforms baseline approaches in accuracy and robustness.
Author Information
Xiangru Huang (University of Texas at Austin)
Haitao Yang (University of Texas at Austin)
Etienne Vouga (The University of Texas at Austin)
Qixing Huang (The University of Texas at Austin)
More from the Same Authors
-
2022 : Neural Volumetric Mesh Generator »
Yan Zheng · Lemeng Wu · Xingchao Liu · Zhen Chen · Qiang Liu · Qixing Huang -
2023 Poster: Jigsaw: Learning to Assemble Multiple Fractured Objects »
Jiaxin Lu · Yifan Sun · Qixing Huang -
2019 Poster: A Condition Number for Joint Optimization of Cycle-Consistent Networks »
Leonidas Guibas · Qixing Huang · Zhenxiao Liang -
2019 Spotlight: A Condition Number for Joint Optimization of Cycle-Consistent Networks »
Leonidas Guibas · Qixing Huang · Zhenxiao Liang