# UV R-CNN: Stable and Efficient Dense Human Pose Estimation Source: [UV R-CNN: Stable and Efficient Dense Human Pose Estimation]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:45:11.347Z Authors: Wenhe Jia, Yilin Zhou, Xuhan Zhu, Mengjie Hu, Chun Liu, Qing Song Published: 2022-11-04T09:29:04.000Z ## Abstract 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. By analyzing the loss formulation of the existing dense pose estimation model, we 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, we propose a brand new architecture, named UV R-CNN. Without auxiliary supervision and external knowledge from other tasks, UV R-CNN can handle many complicated issues in dense pose model training progress, achieving 65.0% $AP\_{gps}$ and 66.1% $AP\_{gpsm}$ on the DensePose-COCO validation subset with ResNet-50-FPN feature extractor, competitive among the state-of-the-art dense human pose estimation methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()