AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features

TL;DR

AuxDepthNet is a real-time monocular 3D object detection framework that learns depth-sensitive features without external depth maps, achieving state-of-the-art results on KITTI.

Contribution

It introduces the ADF and DPM modules within a DepthFusion Transformer to improve spatial reasoning and object localization without external depth estimators.

Findings

Achieves state-of-the-art AP scores on KITTI dataset.

Operates in real-time without external depth maps.

Demonstrates robustness across different difficulty levels.

Abstract

Monocular 3D object detection is a challenging task in autonomous systems due to the lack of explicit depth information in single-view images. Existing methods often depend on external depth estimators or expensive sensors, which increase computational complexity and hinder real-time performance. To overcome these limitations, we propose AuxDepthNet, an efficient framework for real-time monocular 3D object detection that eliminates the reliance on external depth maps or pre-trained depth models. AuxDepthNet introduces two key components: the Auxiliary Depth Feature (ADF) module, which implicitly learns depth-sensitive features to improve spatial reasoning and computational efficiency, and the Depth Position Mapping (DPM) module, which embeds depth positional information directly into the detection process to enable accurate object localization and 3D bounding box regression. Leveraging the DepthFusion Transformer architecture, AuxDepthNet globally integrates visual and depth-sensitive features through depth-guided interactions, ensuring robust and efficient detection. Extensive experiments on the KITTI dataset show that AuxDepthNet achieves state-of-the-art performance, with $\text{AP}_{3D}$ scores of 24.72\% (Easy), 18.63\% (Moderate), and 15.31\% (Hard), and $\text{AP}_{\text{BEV}}$ scores of 34.11\% (Easy), 25.18\% (Moderate), and 21.90\% (Hard) at an IoU threshold of 0.7.