Skip to main content
Fig. 6 | IPSJ Transactions on Computer Vision and Applications

Fig. 6

From: 3D human pose estimation model using location-maps for distorted and disconnected images by a wearable omnidirectional camera

Fig. 6

The network architecture of our model based on HRNet-W24. The stem net convolutes input images to 256 (channel) ×24 (input height /4) ×48 (input width /4) regardless of the number of W. The network makes branches after the stem net according to W. The number of output maps is 48 because of 4 maps (H, X, Y, and Z) for each of the 12 joints in our setting

Back to article page