Open3D-ML
Entity
Open3D-ML | Entity | |
---|---|---|
1 | 2 | |
1,686 | 668 | |
2.4% | 2.4% | |
5.5 | 6.9 | |
about 2 months ago | 5 months ago | |
Python | Jupyter Notebook | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Open3D-ML
-
Looking for Point Cloud deep learning, training sources
I already have a basic understanding with Open3D-ML and manage to get examples for training to work. However, my knowledge is not sufficient to transfer this to my own data or model deployment.
Entity
- Open-world entity segmentation: eliminates the thing-stuff distinction!
-
[R] Open-World Entity Segmentation (Better dense image segmentation without labels)
Abstract: We introduce a new image segmentation task, termed Entity Segmentation (ES) with the aim to segment all visual entities in an image without considering semantic category labels. It has many practical applications in image manipulation/editing where the segmentation mask quality is typically crucial but category labels are less important. In this setting, all semantically-meaningful segments are equally treated as categoryless entities and there is no thing-stuff distinction. Based on our unified entity representation, we propose a center-based entity segmentation framework with two novel modules to improve mask quality. Experimentally, both our new task and framework demonstrate superior advantages as against existing work. In particular, ES enables the following: (1) merging multiple datasets to form a large training set without the need to resolve label conflicts; (2) any model trained on one dataset can generalize exceptionally well to other datasets with unseen domains. Our code is made publicly available at this https URL.
What are some alternatives?
CPPE-Dataset - Code for our paper CPPE - 5 (Medical Personal Protective Equipment), a new challenging object detection dataset
rankseg - [JMLR 2023] RankSEG: A consistent ranking-based framework for segmentation
EPro-PnP - [CVPR 2022 Oral, Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
flying-guide-dog - Official implementation of "Flying Guide Dog: Walkable Path Discovery for the Visually Impaired Utilizing Drones and Transformer-based Semantic Segmentation", IEEE ROBIO 2021
nncf - Neural Network Compression Framework for enhanced OpenVINO™ inference
mask-rcnn - Mask-RCNN training and prediction in MATLAB for Instance Segmentation
deepvision - PyTorch and TensorFlow/Keras image models with automatic weight conversions and equal API/implementations - Vision Transformer (ViT), ResNetV2, EfficientNetV2, NeRF, SegFormer, MixTransformer, (planned...) DeepLabV3+, ConvNeXtV2, YOLO, etc.
InteractiveAnnotation - Interactive Annotation using Segment Anything for fast and accurate segmentation
pytorch_geometric - Graph Neural Network Library for PyTorch
fashion-segmentation - A tensorflow model for segmentation of fashion items out of multiple product images
RiverREM - Make river relative elevation models (REM) and REM visualizations from an input digital elevation model (DEM).
AgML - AgML is a centralized framework for agricultural machine learning. AgML provides access to public agricultural datasets for common agricultural deep learning tasks, with standard benchmarks and pretrained models, as well the ability to generate synthetic data and annotations.