Depth data holds significant importance in numerous applications, ranging from video games to autonomous vehicles. Depth data can be acquired by sensors such as LiDAR sensors. Frequently, acquired depth map has holes or data that presents low confidence level. The task of depth data interpolation or completion stands as a fundamental requirement for such applications. Infinity Laplacian is an interpolator of data that can perform this task. The Infinity Laplacian represents the most straightforward interpolator, adhering to a set of appropriate axioms. In this study, we assessed three different variations of the infinity Laplacian for the purpose of completing sparse depth data. We sub-sampled the publicly available NUY_V2 dataset and evaluated the performance of these models by up-sampling depth data. In this paper, we compared the infinity Laplacian, unbalanced infinity Laplacian, balanced infinity Laplacian, and biased infinity Laplacian. Obtained results show that the balanced infinity Laplacian outperforms the other three models and also many contemporaneous models. The addition of a mechanism that balances between two eikonal operators gives the infinity the capability to reach better performance in the up-sampling task. Moving forward, our focus will be directed towards addressing the challenge of edge interpolation using the color reference image.