Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery

by   Mugalodi Rakesh, et al.

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).


page 2

page 4

page 5

page 7

page 8


Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation

Available 3D human pose estimation approaches leverage different forms o...

A Unified Framework for Domain Adaptive Pose Estimation

While pose estimation is an important computer vision task, it requires ...

Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation

Estimation of 3D human pose from monocular image has gained considerable...

Prior-guided Source-free Domain Adaptation for Human Pose Estimation

Domain adaptation methods for 2D human pose estimation typically require...

Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation

We present a deployment friendly, fast bottom-up framework for multi-per...

Alleviating Human-level Shift : A Robust Domain Adaptation Method for Multi-person Pose Estimation

Human pose estimation has been widely studied with much focus on supervi...

Please sign up or login with your details

Forgot password? Click here to reset