CLERF uses contrastive learning with GAN-generated same-pose pairs and geometric augmentation to achieve full-range, including upside-down, head pose estimation, matching or beating prior models on standard and transformed benchmarks.
On the represen- tation and methodology for wide and short range head pose estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CLERF: Contrastive LEaRning for Full Range Head Pose Estimation
CLERF uses contrastive learning with GAN-generated same-pose pairs and geometric augmentation to achieve full-range, including upside-down, head pose estimation, matching or beating prior models on standard and transformed benchmarks.