Better map 2D image points of people to 3D surfaces using novel loss function with UV R-CNN
Better map 2D image points of people to 3D surfaces using novel loss function with UV R-CNN
UV R-CNN: Stable and Efficient Dense Human Pose Estimation
arXiv paper abstract https://arxiv.org/abs/2211.02337
arXiv PDF paper https://arxiv.org/pdf/2211.02337.pdf
Dense pose estimation is a dense 3D prediction task for instance-level human analysis, aiming to map human pixels from an RGB image to a 3D surface of the human body.
Due to a large amount of surface point regression, the training process appears to be easy to collapse compared to other region-based human instance analyzing tasks.
... introduce a novel point regression loss function, named Dense Points} loss to stable the training progress, and a new balanced loss weighting strategy to handle the multi-task losses.
With the above novelties, ... propose a brand new architecture, named UV R-CNN.
... achieving 65.0% APgps and 66.1% APgpsm on the DensePose-COCO validation subset with ResNet-50-FPN feature extractor, competitive among the state-of-the-art dense human pose estimation methods.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Komentarze