3D Object Recognition
27 papers with code • 4 benchmarks • 8 datasets
3D object recognition is the task of recognising objects from 3D data.
Note that there are related tasks you can look at, such as 3D Object Detection which have more leaderboards.
(Image credit: Look Further to Recognize Better)
Benchmarks
These leaderboards are used to track progress in 3D Object Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Datasets
ModelNet
SHREC
Washington RGB-D
Cube++
DOORS
CY101 Dataset
Corn Seeds Dataset
Latest papers
MeshWalker: Deep Mesh Understanding by Random Walks
Each walk is organized as a list of vertices, which in some manner imposes regularity on the mesh.
Triangle-Net: Towards Robustness in Point Cloud Learning
Previous research has shown that points' sparsity, rotation and positional inherent variance can lead to a significant drop in the performance of point cloud based classification techniques.
BlenderProc
BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks.
Task-Aware Monocular Depth Estimation for 3D Object Detection
WXinlong/ForeSeE
•
•
In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders.
SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation
yzhou359/MakeItTalk
•
•
ICCV 2019
In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings.
Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition
We improve upon these methods by introducing a view clustering and pooling layer based on dominant sets.
3D Object Recognition with Ensemble Learning --- A Study of Point Cloud-Based Deep Learning Models
dkoguciuk/ensemble_learning_for_point_clouds
•
•
In this study, we present an analysis of model-based ensemble learning for 3D point-cloud object classification and detection.
OrthographicNet: A Deep Transfer Learning Approach for 3D Object Recognition in Open-Ended Domains
Nowadays, service robots are appearing more and more in our daily life.
PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition
code-implementation1/Code9
•
•
With the recent proliferation of deep learning, various deep models with different representations have achieved the state-of-the-art performance.
Multi-level 3D CNN for Learning Multi-scale Spatial Features
The multi-level voxel representation consists of a coarse voxel grid that contains volumetric information of the 3D object.
