Pose Estimation and 3D Reconstruction of Vehicles from Stereo-Images Using a Subcategory-Aware Shape Prior

TL;DR

This paper introduces a subcategory-aware shape prior and a multi-branch CNN for improved vehicle pose estimation and 3D reconstruction from stereo images, leveraging vehicle type predictions and keypoint extraction.

Contribution

It presents a novel deformable vehicle model with subcategory awareness and a multi-branch CNN for vehicle type, orientation, keypoints, and wireframes, enhancing 3D reconstruction accuracy.

Findings

Outperforms state-of-the-art vehicle pose estimation methods.

Demonstrates the effectiveness of the shape prior on real-world datasets.

Shows improved alignment and reconstruction quality.

Abstract

The 3D reconstruction of objects is a prerequisite for many highly relevant applications of computer vision such as mobile robotics or autonomous driving. To deal with the inverse problem of reconstructing 3D objects from their 2D projections, a common strategy is to incorporate prior object knowledge into the reconstruction approach by establishing a 3D model and aligning it to the 2D image plane. However, current approaches are limited due to inadequate shape priors and the insufficiency of the derived image observations for a reliable alignment with the 3D model. The goal of this paper is to show how 3D object reconstruction can profit from a more sophisticated shape prior and from a combined incorporation of different observation types inferred from the images. We introduce a subcategory-aware deformable vehicle model that makes use of a prediction of the vehicle type for a more appropriate regularisation of the vehicle shape. A multi-branch CNN is presented to derive predictions of the vehicle type and orientation. This information is also introduced as prior information for model fitting. Furthermore, the CNN extracts vehicle keypoints and wireframes, which are well-suited for model-to-image association and model fitting. The task of pose estimation and reconstruction is addressed by a versatile probabilistic model. Extensive experiments are conducted using two challenging real-world data sets on both of which the benefit of the developed shape prior can be shown. A comparison to state-of-the-art methods for vehicle pose estimation shows that the proposed approach performs on par or better, confirming the suitability of the developed shape prior and probabilistic model for vehicle reconstruction.