2 papers
cs.CV2024
Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images
Ammar Qammaz, Nikolaos Vasilikopoulos, Iason Oikonomidis +1
We present Y-MAP-Net, a Y-shaped neural network architecture designed for real-time multi-task learning on RGB images. Y-MAP-Net, simultaneously predicts depth, surface normals, hu…
cs.CV2023
TAPE: Temporal Attention-based Probabilistic human pose and shape Estimation
Nikolaos Vasilikopoulos, Nikos Kolotouros, Aggeliki Tsoli +1
Reconstructing 3D human pose and shape from monocular videos is a well-studied but challenging problem. Common challenges include occlusions, the inherent ambiguities in the 2D to…