DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
This addresses hand-object interaction segmentation for robotics or AR/VR applications, but appears incremental with improvements like dense attention and contour loss.
The paper tackles the problem of segmenting hands from interacted objects in depth inputs, achieving real-time performance and outperforming state-of-the-art deep segmentation methods.
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.