diff --git a/configs/body/3d_kpt_sview_rgb_img/pose_lift/mpi_inf_3dhp/simplebaseline3d_mpi-inf-3dhp.md b/configs/body/3d_kpt_sview_rgb_img/pose_lift/mpi_inf_3dhp/simplebaseline3d_mpi-inf-3dhp.md index 635d4e1399..c520c51e7e 100644 --- a/configs/body/3d_kpt_sview_rgb_img/pose_lift/mpi_inf_3dhp/simplebaseline3d_mpi-inf-3dhp.md +++ b/configs/body/3d_kpt_sview_rgb_img/pose_lift/mpi_inf_3dhp/simplebaseline3d_mpi-inf-3dhp.md @@ -37,6 +37,6 @@ Results on MPI-INF-3DHP dataset with ground truth 2D detections | Arch | MPJPE | P-MPJPE | 3DPCK | 3DAUC | ckpt | log | | :---------------------------------------------------------- | :---: | :-----: | :---: | :---: | :----------------------------------------------------------: | :---------------------------------------------------------: | -| [simple_baseline_3d_tcn1](configs/body/3d_kpt_sview_rgb_img/pose_lift/mpi_inf_3dhp/simplebaseline3d_mpi-inf-3dhp.py) | 84.3 | 53.2 | 85.0 | 52.0 | [ckpt](https://download.openmmlab.com/mmpose/body3d/simple_baseline/simplebaseline3d_mpi-inf-3dhp-b75546f6_20210603.pth) | [log](https://download.openmmlab.com/mmpose/body3d/simplebaseline3d/simplebaseline3d_mpi-inf-3dhp_20210603.log.json) | +| [simple_baseline_3d_tcn1](/configs/body/3d_kpt_sview_rgb_img/pose_lift/mpi_inf_3dhp/simplebaseline3d_mpi-inf-3dhp.py) | 84.3 | 53.2 | 85.0 | 52.0 | [ckpt](https://download.openmmlab.com/mmpose/body3d/simple_baseline/simplebaseline3d_mpi-inf-3dhp-b75546f6_20210603.pth) | [log](https://download.openmmlab.com/mmpose/body3d/simplebaseline3d/simplebaseline3d_mpi-inf-3dhp_20210603.log.json) | 1 Differing from the original paper, we didn't apply the `max-norm constraint` because we found this led to a better convergence and performance. diff --git a/docs/en/tasks/3d_body_mesh.md b/docs/en/tasks/3d_body_mesh.md index aced63c802..5f12ddf789 100644 --- a/docs/en/tasks/3d_body_mesh.md +++ b/docs/en/tasks/3d_body_mesh.md @@ -52,6 +52,11 @@ mmpose ### SMPL Model + + +
+SMPL (TOG'2015) + ```bibtex @article{loper2015smpl, title={SMPL: A skinned multi-person linear model}, @@ -65,6 +70,8 @@ mmpose } ``` +
+ For human mesh estimation, SMPL model is used to generate the human mesh. Please download the [gender neutral SMPL model](http://smplify.is.tue.mpg.de/), [joints regressor](https://download.openmmlab.com/mmpose/datasets/joints_regressor_cmr.npy) @@ -180,18 +187,23 @@ extract the images by themselves. +
+MPI-INF-3DHP (3DV'2017) + ```bibtex @inproceedings{mono-3dhp2017, - author = {Mehta, Dushyant and Rhodin, Helge and Casas, Dan and Fua, Pascal and Sotnychenko, Oleksandr and Xu, Weipeng and Theobalt, Christian}, - title = {Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision}, - booktitle = {3D Vision (3DV), 2017 Fifth International Conference on}, - url = {http://gvv.mpi-inf.mpg.de/3dhp_dataset}, - year = {2017}, - organization={IEEE}, - doi={10.1109/3dv.2017.00064}, + author = {Mehta, Dushyant and Rhodin, Helge and Casas, Dan and Fua, Pascal and Sotnychenko, Oleksandr and Xu, Weipeng and Theobalt, Christian}, + title = {Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision}, + booktitle = {3D Vision (3DV), 2017 Fifth International Conference on}, + url = {http://gvv.mpi-inf.mpg.de/3dhp_dataset}, + year = {2017}, + organization={IEEE}, + doi={10.1109/3dv.2017.00064}, } ``` +
+ For [MPI-INF-3DHP](http://gvv.mpi-inf.mpg.de/3dhp-dataset/), please follow the [preprocess procedure](https://github.com/nkolot/SPIN/tree/master/datasets/preprocess) of SPIN to sample images, and make them like this: @@ -241,6 +253,9 @@ mmpose +
+LSP (BMVC'2010) + ```bibtex @inproceedings{johnson2010clustered, title={Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation.}, @@ -254,6 +269,8 @@ mmpose } ``` +
+ For [LSP](https://sam.johnson.io/research/lsp.html), please download the high resolution version [LSP dataset original](http://sam.johnson.io/research/lsp_dataset_original.zip). Extract them under `$MMPOSE/data`, and make them look like this: @@ -277,6 +294,9 @@ mmpose +
+LSPET (CVPR'2011) + ```bibtex @inproceedings{johnson2011learning, title={Learning effective human pose estimation from inaccurate annotation}, @@ -288,6 +308,8 @@ mmpose } ``` +
+ For [LSPET](https://sam.johnson.io/research/lspet.html), please download its high resolution form [HR-LSPET](http://datasets.d2.mpi-inf.mpg.de/hr-lspet/hr-lspet.zip). Extract them under `$MMPOSE/data`, and make them look like this: @@ -313,6 +335,9 @@ mmpose +
+CMU MoShed (CVPR'2018) + ```bibtex @inproceedings{kanazawa2018end, title={End-to-end recovery of human shape and pose}, @@ -323,6 +348,8 @@ mmpose } ``` +
+ Real-world SMPL parameters are used for the adversarial training in human mesh estimation. The MoShed data provided in [HMR](https://github.com/akanazawa/hmr) is included in this [zip file](https://download.openmmlab.com/mmpose/datasets/mesh_annotation_files.zip).