Embedded Files
Abstract
Abstract
Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at deployment is highly inconvenient. However, we realize that standard foreground silhouette estimation techniques (on static camera feeds) remain unaffected by domain-shifts. Motivated by this, we propose a novel target adaptation framework that relies only on silhouette supervision to adapt a source-trained model-based regressor. However, in the absence of any auxiliary cue (multi-view, depth, or 2D pose), an isolated silhouette loss fails to provide a reliable pose-specific gradient and requires to be employed in tandem with a topology-centric loss. To this end, we develop a series of convolution-friendly spatial transformations in order to disentangle a topological-skeleton representation from the raw silhouette. Such a design paves the way to devise a Chamfer-inspired spatial topological-alignment loss via distance field computation, while effectively avoiding any gradient hindering spatial-to-pointset mapping. Experimental results demonstrate our superiority against prior-arts in self-adapting a source trained model to diverse unlabeled target domains, such as a) in-the-wild datasets, b) low-resolution image domains, and c) adversarially perturbed image domains (via UAP).
Citation
Citation
If you find our work helpful, please cite our work:
@inproceedings{align_topo_human,
title={Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery},
author={Rakesh, Mugalodi and Kundu, Jogendra Nath and Jampani, Varun and Babu, R. Venkatesh},
inproceedings={Advances in Neural Information Processing Systems (NeurIPS)},
year={2021}
}
Page updated
Google Sites
Report abuse