3D Object Detection From Monocular Images
11 papers with code • 3 benchmarks • 3 datasets
This is the task of detecting 3D objects from monocular images (as opposed to LiDAR based counterparts). It is usually associated with autonomous driving based tasks.
( Image credit: Orthographic Feature Transform for Monocular 3D Object Detection )
Benchmarks
These leaderboards are used to track progress in 3D Object Detection From Monocular Images
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Waymo Open Dataset
KITTI-360
3D-POP
Latest papers
SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects.
Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
facebookresearch/omni3d
•
•
CVPR 2023
In 3D, existing benchmarks are small in size and approaches specialize in few object categories and specific domains, e. g. urban driving scenes.
DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection
As a result, DEVIANT is equivariant to the depth translations in the projective manifold whereas vanilla networks are not.
MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection
zrrskywalker/monodetr
•
•
ICCV 2023
In this paper, we introduce the first DETR framework for Monocular DEtection with a depth-guided TRansformer, named MonoDETR.
ROCA: Robust CAD Model Retrieval and Alignment from a Single Image
We present ROCA, a novel end-to-end approach that retrieves and aligns 3D CAD models from a shape database to a single input image.
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages.
GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
abhi1kumar/groomed_nms
•
•
CVPR 2021
In this paper, we present and integrate GrooMeD-NMS -- a novel Grouped Mathematically Differentiable NMS for monocular 3D object detection, such that the network is trained end-to-end with a loss on the boxes after NMS.
Delving into Localization Errors for Monocular 3D Object Detection
xinzhuma/monodle
•
•
CVPR 2021
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 challenging.
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
garrickbrazil/M3D-RPN
•
•
ICCV 2019
Understanding the world in 3D is a critical component of urban autonomous driving.
Deep Hough Voting for 3D Object Detection in Point Clouds
open-mmlab/mmdetection3d
•
•
ICCV 2019
Current 3D object detection methods are heavily influenced by 2D detectors.
