UDAPose improves low-light human pose estimation by synthesizing realistic images via DHF and LCIM modules and dynamically balancing image cues with pose priors using DCA, yielding AP gains of 10.1 and 7.4 over prior methods.
Pose estimation for augmented reality: A hands-on survey
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
Reframing head pose estimation as relative pose prediction between image pairs enables a synthetic-only trained model to outperform absolute regression methods on real benchmarks.
The authors present a compact algebraic solver for the P3P problem using the classical Grunert formulation that achieves accuracy and runtime comparable to state-of-the-art methods.
citing papers explorer
-
UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation
UDAPose improves low-light human pose estimation by synthesizing realistic images via DHF and LCIM modules and dynamically balancing image cues with pose priors using DCA, yielding AP gains of 10.1 and 7.4 over prior methods.
-
VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction
Reframing head pose estimation as relative pose prediction between image pairs enables a synthetic-only trained model to outperform absolute regression methods on real benchmarks.
-
P3P Made Easy
The authors present a compact algebraic solver for the P3P problem using the classical Grunert formulation that achieves accuracy and runtime comparable to state-of-the-art methods.