You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
From our experiment, UniPose has a better generalization than OpenPose on multi-person, artificial human, heavy occlusion scenes due to the fully end-to-end training pipeline on diverse datasets. You can simply use this link to try the performance. For the person keypoint detection, input "person" in the "Instance Prompt" and leave "Keypoint Example" alone. If you find multiple redundant outputs, please decrease the "IoU Threshold" in "Advanced options" to 0.1.
Hi @yangjie-cv , @ailingzengzzz et al.,
Such an advanced work on PE. May I ask if uv compared UniPose with OpenPose? Does it outperform? Many thx & best,
The text was updated successfully, but these errors were encountered: