DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax

TL;DR

DepthP+P introduces a novel monocular depth estimation method that achieves metric accuracy by leveraging planar parallax and ground plane alignment, simplifying camera motion prediction.

Contribution

The paper presents a new approach that estimates depth in metric scale by focusing on camera translation and using planar parallax, reducing reliance on full 6DoF motion estimation.

Findings

Achieves metric scale depth estimation on KITTI dataset.

Outperforms traditional self-supervised methods in accuracy.

Simplifies motion prediction by focusing on translation only.

Abstract

Current self-supervised monocular depth estimation methods are mostly based on estimating a rigid-body motion representing camera motion. These methods suffer from the well-known scale ambiguity problem in their predictions. We propose DepthP+P, a method that learns to estimate outputs in metric scale by following the traditional planar parallax paradigm. We first align the two frames using a common ground plane which removes the effect of the rotation component in the camera motion. With two neural networks, we predict the depth and the camera translation, which is easier to predict alone compared to predicting it together with rotation. By assuming a known camera height, we can then calculate the induced 2D image motion of a 3D point and use it for reconstructing the target image in a self-supervised monocular approach. We perform experiments on the KITTI driving dataset and show that the planar parallax approach, which only needs to predict camera translation, can be a metrically accurate alternative to the current methods that rely on estimating 6DoF camera motion.