3D Classification
34 papers with code • 0 benchmarks • 11 datasets
Benchmarks
These leaderboards are used to track progress in 3D Classification
Libraries
Use these libraries to find 3D Classification models and implementationsDatasets
- ShapeNetCore
- ModelNet40-C
- RAD-ChestCT Dataset
- Teeth3DS
- ADHD-200
- Calcium imaging of glomeruli in the olfactory bulb of the mouse in response to thirty-five monomolecular odors
- CVB
- 3D-Point Cloud dataset of various geometrical terrains
- Corn Seeds Dataset
- VIDIMU: Multimodal video and IMU kinematic dataset on daily life activities using affordable devices
Most implemented papers
Multimodal Semi-Supervised Learning for 3D Objects
This paper explores how the coherence of different modelities of 3D data (e. g. point cloud, image, and mesh) can be used to improve data efficiency for both 3D classification and retrieval tasks.
Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network
It results in a serious issue of lagged gradient, making the learned attack at the current step ineffective due to the architecture changes afterward.
M3T: Three-Dimensional Medical Image Classifier Using Multi-Plane and Multi-Slice Transformer
The proposed network synergically combines 3D CNN, 2D CNN, and Transformer for accurate AD classification.
APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification
In the existing work, each point in the cloud may inevitably be selected as the neighbors of multiple aggregation centers, as all centers will gather neighbor features from the whole point cloud independently.
SimpleView++: Neighborhood Views for Point Cloud Classification
Among these methods, the Simple View model demonstrates that features from six orthogonal perspective projections of a point cloud achieved comparable 3D classification.
PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack
Adversarial contrastive learning (ACL) is considered an effective way to improve the robustness of pre-trained models.
Local Neighborhood Features for 3D Classification
We train and evaluate PointNeXt on ModelNet40 (synthetic), ScanObjectNN (real-world), and a recent large-scale, real-world grocery dataset, i. e., 3DGrocery100.
ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
Then, ULIP learns a 3D representation space aligned with the common image-text space, using a small number of automatically synthesized triplets.
MVTN: Learning Multi-View Transformations for 3D Understanding
Multi-view projection techniques have shown themselves to be highly effective in achieving top-performing results in the recognition of 3D shapes.
ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
It achieves a new SOTA of 50. 6% (top-1) on Objaverse-LVIS and 84. 7% (top-1) on ModelNet40 in zero-shot classification.