The large-scale deployment of autonomous vehicles is yet to come, and one of the major
remaining challenges lies in urban dense traffic scenarios. In such cases, it remains …

Semi-supervised object detection is crucial for 3D scene understanding, efficiently
addressing the limitation of acquiring large-scale 3D bounding box annotations. Existing …

Semi-supervised learning (SSL) has promising potential for improving model performance
using both labelled and unlabelled data. Since recovering 3D information from 2D images is …

In this work, we build a modular-designed codebase, formulate strong training recipes,
design an error diagnosis toolbox, and discuss current methods for image-based 3D object …

Monocular 3D object detection (M3OD) is a significant yet inherently challenging task in
autonomous driving due to absence of explicit depth cues in a single RGB image. In this …

We delve into pseudo-labeling for semi-supervised monocular 3D object detection
(SSM3OD) and discover two primary issues: a misalignment between the prediction quality …

Detecting objects in 3D space using multiple cameras, known as Multi-Camera 3D Object
Detection (MC3D-Det), has gained prominence with the advent of bird's-eye view (BEV) …

In this paper, we improve the challenging monocular 3D object detection problem with a
general semi-supervised framework. Specifically, having observed that the bottleneck of this …

Monocular 3D object detection (M3OD) is a significant yet inherently challenging task in
autonomous driving due to absence of implicit depth cues in a single RGB image. In this …

Despite the significant benefits of low cost and scalability associated with monocular 3D
object detection, accurately estimating depth from a single 2D image remains challenging …