Monocular 3D Object Detection
77 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.
Benchmarks
These leaderboards are used to track progress in Monocular 3D Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Monocular 3D Object Detection models and implementations
KITTI
SUN RGB-D
Virtual KITTI
OPV2V
Virtual KITTI 2
Latest papers
Delving into Motion-Aware Matching for Monocular 3D Object Tracking
kuanchihhuang/moma-m3t
•
•
ICCV 2023
In this paper, we find that the motion cue of objects along different time frames is critical in 3D multi-object tracking, which is less explored in existing monocular-based approaches.
MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection
cskkxjk/mononerd
•
•
ICCV 2023
To the best of our knowledge, this work is the first to introduce volume rendering for M3D, and demonstrates the potential of implicit reconstruction for image-based 3D perception.
VCVW-3D: A Virtual Construction Vehicles and Workers Dataset with 3D Annotations
Currently, object detection applications in construction are almost based on pure 2D data (both image and annotation are 2D-based), resulting in the developed artificial intelligence (AI) applications only applicable to some scenarios that only require 2D information.
Learning Occupancy for Monocular 3D Object Detection
Monocular 3D detection is a challenging task due to the lack of accurate 3D information.
SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection
To tackle this problem, this paper proposes a novel "Supervised Scale-aware Deformable Attention" (SSDA) for monocular 3D object detection.
SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer
mit-han-lab/sparsevit
•
•
CVPR 2023
High-resolution images enable neural networks to learn richer visual representations.
3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection
drilistbox/3dppe
•
•
ICCV 2023
Although 3D measurements are not available at the inference time of monocular 3D object detection, 3DPPE uses predicted depth to approximate the real point positions.
OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection
Unfortunately, the network cannot accurately distinguish different depths from such non-discriminative visual features, resulting in unstable depth training.
3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers
drilistbox/3dppe
•
•
Although 3D measurements are not available at the inference time of monocular 3D object detection, 3DPPE uses predicted depth to approximate the real point positions.
Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection
Cc-Hy/CMKD
•
•
Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e. g., Pseudo-LiDAR methods.
