mmpose/configs/wholebody_2d_keypoint/topdown_heatmap

Top-down heatmap-based pose estimation

Top-down methods divide the task into two stages: object detection, followed by single-object pose estimation given object bounding boxes. Instead of estimating keypoint coordinates directly, the pose estimator will produce heatmaps which represent the likelihood of being a keypoint, following the paradigm introduced in Simple Baselines for Human Pose Estimation and Tracking.

Results and Models

COCO-WholeBody Dataset

Results on COCO-WholeBody v1.0 val with detector having human AP of 56.4 on COCO val2017 dataset

Model	Input Size	Whole AP	Whole AR	Details and Download
HRNet-w48+Dark+	384x288	0.661	0.743	hrnet_dark_coco-wholebody.md
HRNet-w32+Dark	256x192	0.582	0.671	hrnet_dark_coco-wholebody.md
HRNet-w48	256x192	0.579	0.681	hrnet_coco-wholebody.md
CSPNeXt-m	256x192	0.567	0.641	cspnext_udp_coco-wholebody.md
ResNet-152	256x192	0.548	0.661	resnet_coco-wholebody.md
HRNet-w32	256x192	0.536	0.636	hrnet_coco-wholebody.md
ResNet-101	256x192	0.531	0.645	resnet_coco-wholebody.md
S-ViPNAS-Res50+Dark	256x192	0.528	0.632	vipnas_dark_coco-wholebody.md
ResNet-50	256x192	0.521	0.633	resnet_coco-wholebody.md
S-ViPNAS-Res50	256x192	0.495	0.607	vipnas_coco-wholebody.md