Apr 26, 2022 � ViTPose employs plain and non-hierarchical vision transformers as backbones to extract features for a given person instance and a lightweight decoder for pose�...

This branch contains the pytorch implementation of ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation and ViTPose+: Vision Transformer�...

1) We propose a simple yet effective baseline model named ViTPose for human pose estimation. It obtains SOTA performance on the MS COCO. Keypoint dataset even�...

Apr 3, 2024 � ViTPose employs plain and non-hierarchical vision transformers as backbones to extract features for a given person instance and a lightweight decoder for pose�...

This paper shows the surprisingly good properties of plain vision transformers for body pose estimation from various aspects.

ViTPose employs plain and non-hierarchical vision transformers as backbones to extract features for a given person instance and a lightweight decoder for pose�...

Jul 19, 2023 � It provides a simple baseline for vision transformer-based human pose estimation. It utilises a pretrained vision transformer backbone to extract features.

We demonstrate that a plain vision transformer with MAE pretraining can obtain superior performance after finetuning on human pose estimation datasets.

ViTPose employs the plain and non-hierarchical vision transformer as an encoder to encode features and a lightweight decoder to decode body keypoints in either�...