mmpose/configs/face_2d_keypoint/topdown_regression

Top-down regression-based pose estimation

Top-down methods divide the task into two stages: object detection, followed by single-object pose estimation given object bounding boxes. At the 2nd stage, regression based methods directly regress the keypoint coordinates given the features extracted from the bounding box area, following the paradigm introduced in Deeppose: Human pose estimation via deep neural networks.

Results and Models

WFLW Dataset

Result on WFLW test set

Model	Input Size	NME	ckpt	log
ResNet-50	256x256	4.88	ckpt	log
ResNet-50+WingLoss	256x256	4.67	ckpt	log
ResNet-50+SoftWingLoss	256x256	4.44	ckpt	log