Abstract 3D object detection and pose estimation from a single-view image is challenging
due to the high uncertainty caused by the absence of 3D perception. As a solution recent …

In this paper we propose an approach for monocular 3D object detection from a single RGB
image, which leverages a novel disentangling transformation for 2D and 3D detection losses …

Perceiving 3D objects from monocular inputs is crucial for robotic systems, given its
economy compared to multi-sensor settings. It is notably difficult as a single image can not …

This paper investigates the geometric consistency for monocular 3D object detection, which
suffers from the ill-posed depth estimation. We first conduct a thorough analysis to reveal …

Object localization in 3D space is a challenging aspect in monocular 3D object detection.
Recent advances in 6DoF pose estimation have shown that predicting dense 2D-3D …

We propose a novel approach for monocular 3D object detection by leveraging local
perspective effects of each object. While the global perspective effect shown as size and …

We present MonoPSR, a monocular 3D object detection method that leverages proposals
and shape reconstruction. First, using the fundamental relations of a pinhole camera model …

Estimating 3D bounding boxes from monocular images is an essential component in
autonomous driving, while accurate 3D object detection from this kind of data is very …

As an inherently ill-posed problem, depth estimation from single images is the most
challenging part of monocular 3D object detection (M3OD). Many existing methods rely on …

Mobile monocular 3D object detection (Mono3D)(eg, on a vehicle, a drone, or a robot) is an
important yet challenging task. Existing transformer-based offline Mono3D models adopt …