Monocular 3D Object Detection

74 papers with code • 15 benchmarks • 5 datasets

Monocular 3D Object Detection is the task to draw 3D bounding box around objects in a single 2D RGB image. It is localization task but without any extra information like depth or other sensors or multiple-images.

Libraries

Use these libraries to find Monocular 3D Object Detection models and implementations

Latest papers with no code

Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection

no code yet • 26 Mar 2024

Additionally, we present a DepthGradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels, effectively decoupling the depth gradient and removing conflicting gradients.

Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator

no code yet • 6 Mar 2024

Real-time processing is crucial in autonomous driving systems due to the imperative of instantaneous decision-making and rapid response.

UniMODE: Unified Monocular 3D Object Detection

no code yet • 28 Feb 2024

To address these challenges, we build a detector based on the bird's-eye-view (BEV) detection paradigm, where the explicit feature projection is beneficial to addressing the geometry learning ambiguity when employing multiple scenarios of data to train detectors.

You Only Look Bottom-Up for Monocular 3D Object Detection

no code yet • 27 Jan 2024

Monocular 3D Object Detection is an essential task for autonomous driving.

Depth-discriminative Metric Learning for Monocular 3D Object Detection

no code yet • NeurIPS 2023

Moreover, we introduce an auxiliary head for object-wise depth estimation, which enhances depth quality while maintaining the inference time.

Rotation Matters: Generalized Monocular 3D Object Detection for Various Camera Systems

no code yet • 9 Oct 2023

In this paper, we conduct extensive experiments to analyze the factors that cause performance degradation.

Every Dataset Counts: Scaling up Monocular 3D Object Detection with Joint Datasets Training

no code yet • 2 Oct 2023

Monocular 3D object detection plays a crucial role in autonomous driving.

MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddings

no code yet • 30 Sep 2023

We discover that most existing monocular 3D object detectors rely on the ego-vehicle prior assumption that the optical axis of the camera is parallel to the ground.

Polygon Intersection-over-Union Loss for Viewpoint-Agnostic Monocular 3D Vehicle Detection

no code yet • 13 Sep 2023

Monocular 3D object detection is a challenging task because depth information is difficult to obtain from 2D images.

S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection

no code yet • 2 Sep 2023

These methods typically use visual and depth representations to generate query points on objects, whose quality plays a decisive role in the detection accuracy.