We propose a real-time DNN-based technique to segment hand and object of interacting motions from depth inputs. Our model is called DenseAttentionSeg, which contains a dense attention mechanism to fuse information in different scales and improves the results quality with skip-connections. Besides, we introduce a contour loss in model training, which helps to generate accurate hand and object boundaries. Finally, we propose and release our InterSegHands dataset, a fine-scale hand segmentation dataset containing about 52k depth maps of hand-object interactions. Our experiments evaluate the effectiveness of our techniques and datasets, and indicate that our method outperforms the current state-of-the-art deep segmentation methods on interaction segmentation.
@article{arxiv.1903.12368,
title = {DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input},
author = {Zihao Bo and Hao Zhang and Junhai Yong and Feng Xu},
journal= {arXiv preprint arXiv:1903.12368},
year = {2020}
}