Combine

Introduction

We provide the config files for training and pretrained models for inference on the optimal configurations.

Notes

Download the pretrained backbones from here:

1. resnet50_coco_pose.pth
2. hrnet_coco_pose.pth
3. twins_svt_coco_pose.pth

Download the above resources and arrange them in the following file structure:

mmhuman3d
├── mmhuman3d
├── docs
├── tests
├── tools
├── configs
└── data
    └── checkpoints
        ├── resnet50_coco_pose.pth
        ├── hrnet_coco_pose.pth
        └── twins_svt_coco_pose.pth

Results and Models

We evaluate HMR on 3DPW. Values are PA-MPJPE.

Config	Dataset	Backbone	3DPW	Download
resnet50_hmr_mix1_coco_l1.py	H36M, MI, COCO, LSP, LSPET, MPII	ResNet-50	51.66	model
hrnet_hmr_mix1_coco_l1.py	H36M, MI, COCO, LSP, LSPET, MPII	HRNet-W32	49.18	model
twins_svt_hmr_mix1_coco_l1.py	H36M, MI, COCO, LSP, LSPET, MPII	Twins-SVT	48.77	model
twins_svt_hmr_mix1_coco_l1_aug.py	H36M, MI, COCO, LSP, LSPET, MPII	Twins-SVT	47.70	model
hrnet_hmr_mix4_coco_l1_aug.py	EFT-[COCO, LSPET, MPII], H36M, SPIN-MI	HRNet-W32	47.68	model
twins_svt_hmr_mix4_coco_l1.py	EFT-[COCO, LSPET, MPII], H36M, SPIN-MI	Twins-SVT	47.31	model
hrnet_hmr_mix2_coco_l1_aug.py	H36M, MI, EFT-COCO	HRNet-W32	48.08	model
twins_svt_hmr_mix2_coco_l1.py	H36M, MI, EFT-COCO	Twins-SVT	48.27	model
twins_svt_hmr_mix6_coco_l1.py	H36M, MuCo, EFT-COCO	Twins-SVT	47.92	model