基于非局部随机游走和运动补偿的2D转3D优化方法

Optimization for 2D-to-3D conversion based on nonlocal random walk and motion compensation

2D转3D技术可以从2D资源中获取深度信息,以满足3D显示对3D内容的需求。针对2D转3D深度估计中的深度优化问题,提出一种基于非局部随机游走(NRW)和运动补偿的深度优化算法。本文方法在采用NRW和移动双边滤波(SBF)获得关键帧和非关键帧深度图的基础上,为了锐化非关键帧深度序列对象边界,结合纹理信息利用NRW算法优化深度图,同时又考虑相邻帧间的时域信息,采用运动补偿的方法对非关键帧深度序列进行优化,获得高质量的深度视频序列。实验结果表明,本文方法可以得到对象边界更加准确的深度视频估计结果。

Depth information can be obtained from 2-dimensional （2D） resources through 2D-to-3D con- version technology,in order to meet the demand for 3D content. In this paper,a novel approach based on nonlocal random walk （NRW） and motion compensation is proposed to solve the problem of depth map optimization in depth estimation. The depth maps of key frames and non-key frames are obtained on the basis of NRW and shifted bilateral filtering （SBF）, respectively. In order to sharpen the depth bounda- ries, taking texture information into account, NRW is utilized to optimize the depth sequence. Considering that the temporal information of adjacent frames, motion compensation is introduced to further improve the quality of depth maps of non-key frames. Experimental results show that,in contrast to the method directly processed by SBF, our method can produce higher quality depth sequence with accurate object boundaries.