By regressing coefficients of precomputed DCT or SVD trajectory bases, a network reconstructs 3D poses for every frame in a video and outperforms prior video-based pose estimators on Human3.6M and MPI-INF-3DHP under several protocols.
Keep it smpl: Automatic estimation of 3d human pose and shape from a single image
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation
By regressing coefficients of precomputed DCT or SVD trajectory bases, a network reconstructs 3D poses for every frame in a video and outperforms prior video-based pose estimators on Human3.6M and MPI-INF-3DHP under several protocols.