Experimental results demonstrate that the proposed method removes unwanted scribbles successfully while preserving expected input, and it outperforms the state-of-the-art when presented with cross-boundary scribbles.ĢD-to-3D conversion aims to estimate depth from 2D images and generates stereoscopic views from the depth, which is a key technology to produce 3D content.
Input confidence based on residuals avoids the propagation of unwanted scribbles and thus enables to generate high-quality depth even with cross-boundary input. The procedure is repeated until a maximum number of iterations is exceeded. Secondly, the residual-driven optimization is performed to estimate dense depth from user scribbles. Firstly, confidence of user input is computed from residuals between the estimation and user-specified depth values, and it is applied to the data fidelity term. To address this problem, a residual-driven energy function is proposed to remove unwanted input introduced by cross-boundary scribbles while preserving expected user input. The performance of most methods degrades significantly when cross-boundary scribbles are present due to their inability to remove unwanted input.
Semi-automatic 2D-to-3D conversion provides a cost-effective solution to the problem of 3D content shortage.
0 kommentar(er)
