Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision

TL;DR

This paper introduces an object-centric depth supervision method that enhances monocular 3D object detection by jointly training detection and depth prediction using raw LiDAR data, improving accuracy and efficiency.

Contribution

The paper proposes a novel object-centric depth loss and an end-to-end training framework that leverages raw LiDAR points without extra annotation, boosting monocular 3D detection performance.

Findings

Outperforms depth map approaches on KITTI and nuScenes

Maintains real-time inference speed

Significantly improves 3D detection accuracy

Abstract

Recent advances in monocular 3D detection leverage a depth estimation network explicitly as an intermediate stage of the 3D detection network. Depth map approaches yield more accurate depth to objects than other methods thanks to the depth estimation network trained on a large-scale dataset. However, depth map approaches can be limited by the accuracy of the depth map, and sequentially using two separated networks for depth estimation and 3D detection significantly increases computation cost and inference time. In this work, we propose a method to boost the RGB image-based 3D detector by jointly training the detection network with a depth prediction loss analogous to the depth estimation task. In this way, our 3D detection network can be supervised by more depth supervision from raw LiDAR points, which does not require any human annotation cost, to estimate accurate depth without explicitly predicting the depth map. Our novel object-centric depth prediction loss focuses on depth around foreground objects, which is important for 3D object detection, to leverage pixel-wise depth supervision in an object-centric manner. Our depth regression model is further trained to predict the uncertainty of depth to represent the 3D confidence of objects. To effectively train the 3D detector with raw LiDAR points and to enable end-to-end training, we revisit the regression target of 3D objects and design a network architecture. Extensive experiments on KITTI and nuScenes benchmarks show that our method can significantly boost the monocular image-based 3D detector to outperform depth map approaches while maintaining the real-time inference speed.