基尼指数成本量指导的抗遮挡光场深度估计方法

光场相机能够实现一次拍摄即获得三维场景的多视角信息,在深度估计领域中具有独特优势.但是,当场景中存在复杂遮挡时,现有深度估计方法提取深度信息的精度会明显降低.针对该问题,设计一种基尼指数成本量指导下的抗遮挡光场深度估计方法.首先,利用光场重聚焦方法获得焦栈图像;然后,构造中心视角与其他视角的基尼指数成本量,并根据成本最小原则计算得到初始深度图;最后,结合彩色图进行联合引导滤波,获得最终的高精度的深度图像.实验结果表明,所提方法对复杂场景更加鲁棒,能够在较小的算法复杂度下获取更好的深度估计结果.相比于其他先进方法,所提方法获取的深度图精度更高,图像边缘保留效果更好,在HCI数据集上的MSE₁₀₀指标平均降低约7.8%.

Anti-occlusion light field depth estimation guided by Gini cost volume

The light field camera can record multi-view information of a three-dimensional scene within one shot, which possesses unique advantage especially in depth estimation. However, the accuracy of the depth information extracted by the existing depth estimation method is significantly reduced when there is complex occlusion in the scene. Aiming at this problem, a method for estimating the depth of anti-occlusion light field based on Gini cost volume is proposed. Firstly, the refocusing images are obtained using the light field refocusing algorithm. Then, the Gini cost volume of the central view and other views are constructed. The initial depth map is calculated according to the principle of minimum cost volume. Finally, the initial depth information is combined with the color map for joint guided filtering, and a high-precision depth map is obtained. The experimental results show that the proposed method is more robust for complex scenes and can obtain better depth estimation results with smaller algorithm complexity. Compared to other advanced methods, the depth images obtained by using the proposed method are more accurate, the edges are clearer, and the MSE₁₀₀ indicator on HCI dataset is reduced by an average of 7.8%.