Realizing Half-Diminished Reality from Video Stream of Manipulating Objects
This addresses a specific visualization issue for users watching object manipulation videos, but it is incremental as it builds on existing Half-Diminished Reality methods.
The paper tackled the problem of hands obscuring objects in manipulation videos by making hands semi-transparent to reveal the objects, achieving real-time processing with verification of good performance.
When we watch a video, in which human hands manipulate objects, these hands may obscure some parts of those objects. We are willing to make clear how the objects are manipulated by making the image of hands semi-transparent, and showing the complete images of the hands and the object. By carefully choosing a Half-Diminished Reality method, this paper proposes a method that can process the video in real time and verifies that the proposed method works well.