PointCLIP_V2
PointCLIP V2 framework
A 3D open-world learning framework that improves performance by utilizing realistic shape projection and language representations.
[ICCV 2023] PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning
235 stars
9 watching
14 forks
Language: Python
last commit: about 2 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| | This is an implementation of the PointNet algorithm in PyTorch for 3D point cloud classification and segmentation tasks. | 2,175 |
| | A deep learning framework for processing 3D point cloud data to extract relevant features for classification and segmentation tasks. | 1,388 |
| | Provides C++ libraries and tools for multi primitive-to-primitive point cloud registration and processing pipelines. | 176 |
| | A PyTorch framework for building and training deep learning models on point clouds. | 224 |
| | Software implementing 3D pointset registration algorithm | 446 |
| | Creates simplified surfaces from dense point clouds using either Delaunay or grid triangulation methods | 10 |
| | A framework for large-scale cross-modal benchmarks and vision-language tasks in Chinese | 157 |
| | Develops a deep learning model for domain adaptation on 3D point cloud data | 130 |
| | An efficient framework for end-to-end learning on image-text and video-text tasks | 709 |
| | A deep learning framework for 3D point cloud analysis, specifically for change detection and segmentation tasks. | 31 |
| | Fast triangulation of polygons | 5 |
| | A software framework for building 3D models using constructive solid geometry in ActionScript 3. | 8 |
| | A collection of Matlab classes for working with point clouds and aligning multiple 3D point sets using the Iterative Closest Point (ICP) algorithm. | 118 |
| | A PyTorch-based framework for 3D scene understanding with holistic context graph and relation-based optimization in panoramic images | 90 |
| | Automates classification and labeling of urban 3D point clouds using data fusion and region growing techniques. | 170 |