The hand keypoint detection accuracy has been notably improved.
Pose Anything
We are glad to support the inference for the category-agnostic pose estimation method [PoseAnything](https://github.com/open-mmlab/mmpose/tree/main/projects/pose_anything)!
You can now specify ANY keypoints you want the model to detect, without needing extra training. Under the project folder:
1. Download the [pretrained model](https://drive.google.com/file/d/1RT1Q8AMEa1kj6k9ZqrtWIKyuR4Jn4Pqc/view?usp=drive_link)
2. Run:
python demo.py --support [path_to_support_image] --query [path_to_query_image] --config configs/demo_b.py --checkpoint [path_to_pretrained_ckpt]
- Thanks to the author of PoseAnything (orhir) for supporting their excellent work!
New Datasets
We have added support for two new datasets:
- (CVPR 2023) [ExLPose](https://mmpose.readthedocs.io/en/latest/dataset_zoo/2d_body_keypoint.html#exlpose-dataset)
- (ICCV 2023) [H3WB](/docs/en/dataset_zoo/3d_wholebody_keypoint.md)
(CVPR 2023) ExLPose
ExLPose builds a new dataset of real low-light images with accurate pose labels. It can be helpful on tranining a pose estimation model working under extreme light conditions.
- Thanks Yang-Changhui for helping with the integration of ExLPose!
- This is the task of our OpenMMLabCamp, if you also wish to contribute code to us, feel free to refer to [this link](https://github.com/open-mmlab/OpenMMLabCamp/discussions/categories/mmpose) to pick up the task!
(ICCV 2023) H3WB
H3WB (Human3.6M 3D WholeBody) extends the Human3.6M dataset with 3D whole-body annotations using the COCO wholebody skeleton. This dataset enables more comprehensive 3D pose analysis and benchmarking for whole-body methods.
- Supported by xiexinch.
Contributors
Tau-J
Ben-Louis
xiexinch
Yang-Changhui
orhir
RFYoung
yao5401
icynic
Jendker
willyfh
jit-a3
Ginray