Marta Cosano

Hello @armangrigoryan96 ! Did you train with your own full body images? Did you achieve good results? Thank you!

Hello! the agnostic image and segmentation map are from the VITON-HD repository and the densepose is from detectron2

Hello @tiamo405 ! you can use OpenPose with configuration BODY_25 (25 keypoints) to extract the pose, instead of coco (18 keypoints).Here there's a photo of both configurations: https://www.researchgate.net/figure/Architecture-of-the-different-modules-to-recognise-poses-and-control-the-robot_fig3_340618434