Depth Completion using Piecewise Planar Model
This work provides an incremental improvement in depth map completion for computer vision applications by reducing artifacts at object boundaries.
The paper addresses artifacts in depth map completion caused by inconsistencies between color and depth boundaries by proposing a piecewise planar model. This model represents the depth map as a collection of 3D planes, and the reconstruction is formulated as an optimization of planar parameters, resulting in high resistance to false object boundaries and visually pleasant 3D point clouds on the KITTI dataset.
A depth map can be represented by a set of learned bases and can be efficiently solved in a closed form solution. However, one issue with this method is that it may create artifacts when colour boundaries are inconsistent with depth boundaries. In fact, this is very common in a natural image. To address this issue, we enforce a more strict model in depth recovery: a piece-wise planar model. More specifically, we represent the desired depth map as a collection of 3D planar and the reconstruction problem is formulated as the optimization of planar parameters. Such a problem can be formulated as a continuous CRF optimization problem and can be solved through particle based method (MP-PBP) \cite{Yamaguchi14}. Extensive experimental evaluations on the KITTI visual odometry dataset show that our proposed methods own high resistance to false object boundaries and can generate useful and visually pleasant 3D point clouds.