Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation

TL;DR

This paper introduces FADNet, a novel monocular 3D object detection network that uses sequential feature association and depth hint augmentation to improve accuracy without extra priors.

Contribution

FADNet uniquely divides output estimation into groups based on difficulty and employs a depth hint module for explicit supervision, advancing monocular 3D detection methods.

Findings

Competitive performance on KITTI benchmark

No reliance on depth priors or refinement modules

Maintains real-time processing speed

Abstract

Monocular 3D object detection, with the aim of predicting the geometric properties of on-road objects, is a promising research topic for the intelligent perception systems of autonomous driving. Most state-of-the-art methods follow a keypoint-based paradigm, where the keypoints of objects are predicted and employed as the basis for regressing the other geometric properties. In this work, a unified network named as FADNet is presented to address the task of monocular 3D object detection. In contrast to previous keypoint-based methods, we propose to divide the output modalities into different groups according to the estimation difficulty of object properties. Different groups are treated differently and sequentially associated by a convolutional Gated Recurrent Unit. Another contribution of this work is the strategy of depth hint augmentation. To provide characterized depth patterns as hints for depth estimation, a dedicated depth hint module is designed to generate row-wise features named as depth hints, which are explicitly supervised in a bin-wise manner. The contributions of this work are validated by conducting experiments and ablation study on the KITTI benchmark. Without utilizing depth priors, post optimization, or other refinement modules, our network performs competitively against state-of-the-art methods while maintaining a decent running speed.