GAC3D: improving monocular 3D object detection with ground-guide model and adaptive convolution

Abstract

Monocular 3D object detection has recently become prevalent in autonomous driving and navigation applications due to its cost-efficiency and easy-to-embed to existent vehicles. The most challenging task in monocular vision is to estimate a reliable object’s location cause of the lack of depth information in RGB images. Many methods tackle this ill-posed problem by directly regressing the object’s depth or take the depth map as a supplement input to enhance the model’s results. However, the performance relies heavily on the estimated depth map quality, which is bias to the training data. In this work, we propose depth-adaptive convolution to replace the traditional 2D convolution to deal with the divergent context of the image’s features. This lead to significant improvement in both training convergence and testing accuracy. Second, we propose a ground plane model that utilizes geometric constraints in the pose estimation process. With the new method, named GAC3D, we achieve better detection results. We demonstrate our approach on the KITTI 3D Object Detection benchmark, which outperforms existing monocular methods.

eGAC3D: enhancing depth adaptive convolution and depth estimation for monocular 3D object pose detection

“…The depth adaptive convolution layer proposed in our previous work GAC3D ( Bui et al, 2021 ) injects information from depth predictions using pixel-adaptive convolution from Su et al (2019) . We design the detection head with a sequence of a depth adaptive convolution layer with filters, a ReLU activation, and a standard convolution layer.…”

“…Recently, we have proposed an improved monocular 3D object detection named GAC3D ( Bui et al, 2021 ), which leverages the assumption that most objects of interest stand on a ground plane. This hint serves as a solid geometric prior to estimating the object’s distance via 2D-3D re-projection.…”