Weakly Supervised Deep Functional Map for Shape Matching
This work addresses shape matching in computer vision and graphics, offering a weakly supervised approach that improves performance over existing methods.
The paper tackles the problem of shape matching by identifying minimum components for state-of-the-art deep functional maps and proposes a novel framework that achieves state-of-the-art results on benchmark datasets, outperforming fully supervised methods by a significant margin.
A variety of deep functional maps have been proposed recently, from fully supervised to totally unsupervised, with a range of loss functions as well as different regularization terms. However, it is still not clear what are minimum ingredients of a deep functional map pipeline and whether such ingredients unify or generalize all recent work on deep functional maps. We show empirically minimum components for obtaining state of the art results with different loss functions, supervised as well as unsupervised. Furthermore, we propose a novel framework designed for both full-to-full as well as partial to full shape matching that achieves state of the art results on several benchmark datasets outperforming even the fully supervised methods by a significant margin. Our code is publicly available at https://github.com/Not-IITian/Weakly-supervised-Functional-map