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 with no code
Deep Models for Multi-View 3D Object Recognition: A Review
We provide detailed information about existing deep learning-based and transformer-based multi-view 3D object recognition models, including the most commonly used 3D datasets, camera configurations and number of views, view selection strategies, pre-trained CNN architectures, fusion strategies, and recognition performance on 3D classification and 3D retrieval tasks.
SUGAR: Pre-training 3D Visual Representations for Robotics
SUGAR employs a versatile transformer-based model to jointly address five pre-training tasks, namely cross-modal knowledge distillation for semantic learning, masked point modeling to understand geometry structures, grasping pose synthesis for object affordance, 3D instance segmentation and referring expression grounding to analyze cluttered scenes.
FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects
In this work, we address the challenging task of 3D object recognition without the reliance on real-world 3D labeled data.
Fine-grained 3D object recognition: an approach and experiments
In the offline stage, instance-based learning (IBL) is used to form a new category and we use K-fold cross-validation to evaluate the obtained object recognition performance.
Deep Graph Reprogramming
In this paper, we explore a novel model reusing task tailored for graph neural networks (GNNs), termed as "deep graph reprogramming".
InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation
Moreover, they cannot explore which 3D geometric characteristics are essential to alleviate the catastrophic forgetting on old classes of 3D objects.
Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition
We explore which depth representation is better in terms of resulting accuracy and compare early and late fusion techniques for aligning the RGB and depth modalities within the ViT architecture.
TANDEM3D: Active Tactile Exploration for 3D Object Recognition
In this work, we propose TANDEM3D, a method that applies a co-training framework for exploration and decision making to 3D object recognition with tactile signals.
Deep Optical Coding Design in Computational Imaging
The performance of COI systems highly depends on the design of its main components: the CE pattern and the computational method used to perform a given task.
RendNet: Unified 2D/3D Recognizer With Latent Space Rendering
Instead of looking at one format, it is a good solution to utilize the formats of VG and RG together to avoid these shortcomings.
