Monocular Road Planar Parallax Estimation

TL;DR

This paper introduces RPANet, a deep neural network leveraging road plane geometry and planar parallax for monocular 3D scene reconstruction in driving environments, avoiding expensive sensors and complex depth prediction.

Contribution

RPANet uniquely uses planar parallax and a cross-attention module to improve monocular 3D sensing by exploiting scene geometry in driving scenes.

Findings

Achieves accurate 3D reconstruction from monocular images.

Effectively utilizes road plane geometry for scene understanding.

Demonstrates robustness in challenging scenarios.

Abstract

Estimating the 3D structure of the drivable surface and surrounding environment is a crucial task for assisted and autonomous driving. It is commonly solved either by using 3D sensors such as LiDAR or directly predicting the depth of points via deep learning. However, the former is expensive, and the latter lacks the use of geometry information for the scene. In this paper, instead of following existing methodologies, we propose Road Planar Parallax Attention Network (RPANet), a new deep neural network for 3D sensing from monocular image sequences based on planar parallax, which takes full advantage of the omnipresent road plane geometry in driving scenes. RPANet takes a pair of images aligned by the homography of the road plane as input and outputs a $\gamma$ map (the ratio of height to depth) for 3D reconstruction. The $\gamma$ map has the potential to construct a two-dimensional transformation between two consecutive frames. It implies planar parallax and can be combined with the road plane serving as a reference to estimate the 3D structure by warping the consecutive frames. Furthermore, we introduce a novel cross-attention module to make the network better perceive the displacements caused by planar parallax. To verify the effectiveness of our method, we sample data from the Waymo Open Dataset and construct annotations related to planar parallax. Comprehensive experiments are conducted on the sampled dataset to demonstrate the 3D reconstruction accuracy of our approach in challenging scenarios.