Depth Completion using Piecewise Planar Model

TL;DR

This paper introduces a piecewise planar model for depth completion that improves boundary accuracy and produces visually pleasing 3D point clouds, addressing artifacts common in previous methods.

Contribution

The paper proposes a strict piecewise planar model for depth recovery formulated as a continuous CRF optimization, solved efficiently with particle-based methods.

Findings

High resistance to false object boundaries

Produces visually pleasant 3D point clouds

Effective on KITTI dataset

Abstract

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.