DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation
This work addresses hand pose estimation for computer vision applications, but it is incremental as it builds on an existing method with straightforward enhancements.
The paper tackles 3D hand pose estimation from depth maps by improving the DeepPrior method with ResNet layers, data augmentation, and better hand localization, achieving better or similar performance on benchmarks like NYU, ICVL, and MSRA while maintaining simplicity.
DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map. Since its publication early 2015, it has been outperformed by several impressive works. Here we show that with simple improvements: adding ResNet layers, data augmentation, and better initial hand localization, we achieve better or similar performance than more sophisticated recent methods on the three main benchmarks (NYU, ICVL, MSRA) while keeping the simplicity of the original method. Our new implementation is available at https://github.com/moberweger/deep-prior-pp .