An End-to-end Framework for Unconstrained Monocular 3D Hand Pose Estimation
This addresses the challenge of 3D hand pose estimation in unconstrained environments for applications like human-computer interaction, though it appears incremental by building on existing methods with novel components.
The paper tackles the problem of unconstrained 3D hand pose estimation from monocular RGB images by developing an end-to-end framework that predicts hand prior information and infers 3D pose using keypoint annotations, outperforming state-of-the-art methods on standard benchmarks.
This work addresses the challenging problem of unconstrained 3D hand pose estimation using monocular RGB images. Most of the existing approaches assume some prior knowledge of hand (such as hand locations and side information) is available for 3D hand pose estimation. This restricts their use in unconstrained environments. We, therefore, present an end-to-end framework that robustly predicts hand prior information and accurately infers 3D hand pose by learning ConvNet models while only using keypoint annotations. To achieve robustness, the proposed framework uses a novel keypoint-based method to simultaneously predict hand regions and side labels, unlike existing methods that suffer from background color confusion caused by using segmentation or detection-based technology. Moreover, inspired by the biological structure of the human hand, we introduce two geometric constraints directly into the 3D coordinates prediction that further improves its performance in a weakly-supervised training. Experimental results show that our proposed framework not only performs robustly on unconstrained setting, but also outperforms the state-of-art methods on standard benchmark datasets.