AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation
This improves accuracy for computer vision applications like human-computer interaction, though it appears incremental as it builds on existing detection and regression methods.
The paper tackles 3D hand pose estimation by proposing an adaptive weighting regression method that combines detection-based and regression-based approaches, achieving state-of-the-art performance on four public datasets (NYU, ICVL, MSRA, HANDS 2017).
In this paper, we propose an adaptive weighting regression (AWR) method to leverage the advantages of both detection-based and regression-based methods. Hand joint coordinates are estimated as discrete integration of all pixels in dense representation, guided by adaptive weight maps. This learnable aggregation process introduces both dense and joint supervision that allows end-to-end training and brings adaptability to weight maps, making the network more accurate and robust. Comprehensive exploration experiments are conducted to validate the effectiveness and generality of AWR under various experimental settings, especially its usefulness for different types of dense representation and input modality. Our method outperforms other state-of-the-art methods on four publicly available datasets, including NYU, ICVL, MSRA and HANDS 2017 dataset.