search

Vegetebird / StridedTransformer-Pose3D

[TMM 2022] Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
MIT License
335 stars 37 forks source link

Hello, may I ask you a question? This algorithm can process real-time video streams #6

Closed wuxiaolianggit closed 2 years ago

wuxiaolianggit commented 2 years ago

Hello, may I ask you a question? This algorithm can process real-time video streams？ @Vegetebird

speed8928 commented 2 years ago

no

Vegetebird commented 2 years ago

Our method outputs the center frame's 3D posed from a input video.

In real-time applications, the "causal setting", mentioned in [1], is more appropriate, i.e, it takes a video sequence as input and outputs the pose of the final frame.

Our algorithm also can be trained in this "causal setting".

[1] Pavllo, et al. 3D human pose estimation in video with temporal convolutions and semi-supervised training, CVPR 2019.

Allencheng97 commented 2 years ago

Hi, May I ask how to your algorithm in casual setting?