CameraHMR predicts camera field of view from images of people and uses it to improve pseudo ground-truth training data, achieving state-of-the-art 3D human pose and shape accuracy.
Objectron: A large scale dataset of object-centric videos in the wild with pose annota- tions
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
-
CameraHMR: Aligning People with Perspective
CameraHMR predicts camera field of view from images of people and uses it to improve pseudo ground-truth training data, achieving state-of-the-art 3D human pose and shape accuracy.