Open-source alternatives to Pointnet2

We propose a new neural network module dubbed EdgeConv suitable for CNN-based high-level tasks on point clouds including classification and segmentation. EdgeConv is differentiable and can be plugged into existing architectures.

The Point Cloud Library is a collection of C++ algorithms designed for filtering, registering, and analyzing large-scale 3D spatial datasets. It provides a framework for 3D point cloud processing, incorporating tools for spatial data filtering and geometric feature estimation. The library includes specialized systems for aligning multiple spatial datasets into a single unified coordinate system and a rendering engine for the visual inspection and analysis of processed point cloud data. It also features tools for calculating spatial descriptors to identify structural patterns and shapes within

PyTorch3D is a 3D geometric deep learning library and mesh processing toolkit designed for learning from point clouds and complex 3D surface geometries. It provides a collection of reusable components and data structures for deep learning with 3D data, including a framework for training and evaluating neural radiance fields to enable photorealistic view synthesis. The project features a differentiable 3D renderer that converts meshes and point clouds into 2D images while allowing gradients to flow back into the geometry and textures. This enables 3D shape optimization, where mesh geometry, te

Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds

PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

This project is a comprehensive computer vision library for the PyTorch ecosystem, providing a standardized collection of neural network architectures, datasets, and high-performance transformation utilities. It serves as a foundational framework for building, training, and deploying deep learning models, offering a centralized model registry that allows developers to instantiate architectures with pre-trained weights for tasks such as image classification, object detection, and semantic segmentation. The library distinguishes itself through its modular approach to data and compute management

Submanifold sparse convolutional networks

1. Python (with necessary common libraries such as numpy, scipy, etc.) 2. TensorFlow 3. You need to prepare your data in *.mat file with the following format: - 'points': N x 3 array (x, y, z coordinates of the point cloud) - 'labels': N x 1 array (1-based integer per-point labels) - 'category':…

PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019 Wenxuan Wu, Zhongang Qi, Li Fuxin.

SPLATNet: Sparse Lattice Networks for Point Cloud Processing (CVPR2018)

This repo is implementation for PointNet(https://arxiv.org/abs/1612.00593) in pytorch. The model is in pointnet/model.py.

DGL is a Python library for building and training graph neural networks. It functions as a graph message passing framework and a geometric deep learning tool, enabling the development of models that analyze graph-structured data. The library is designed for large-scale graph processing, utilizing distributed training and neighbor sampling to handle datasets with billions of edges. It provides specialized support for heterogeneous graph modeling, allowing for the representation of complex real-world entities with multiple node and edge types. Its capabilities cover a wide range of graph tasks

This project is a modular research toolkit designed for developing, training, and evaluating deep learning models for object detection, segmentation, and video instance tracking. It provides a flexible training engine that manages complex neural network execution, including distributed training, custom lifecycle hooks, and weight optimization. The framework is built around a hierarchical configuration system that allows users to define architectures, data pipelines, and training hyperparameters through composable, inheritable files. The project distinguishes itself through its highly modular

This project is a dataset management framework and cross-framework data loader that provides a unified interface for reading data formats compatible with TensorFlow, JAX, and PyTorch. It serves as a library of curated public datasets provided as data streams and includes tools for building, versioning, and documenting large-scale datasets. The system differentiates itself through a distributed data processing engine capable of managing massive datasets across clusters using parallelized pipelines. It utilizes builder-based construction to standardize how data is downloaded and prepared, while

Lightly is a self-supervised learning framework and computer vision data curation tool designed to manage large image datasets and train models on unlabeled data. It functions as a PyTorch vision library and dataset management SDK, providing tools to convert raw images into high-dimensional vectors for similarity search, visualization, and feature extraction. The project implements a variety of self-supervised architectures, including MoCo, SimCLR, VICReg, Barlow Twins, and masked image modeling. It distinguishes itself by combining these learning frameworks with active learning capabilities,

PCDet is a LiDAR 3D object detection toolbox and point cloud processing library built on the PyTorch deep learning framework. It provides a system for identifying and locating three-dimensional objects within point cloud data. The project utilizes a data-model separation pattern to decouple dataset loading logic from the core detection pipeline. It features a multi-sensor fusion pipeline that combines data from multiple sensors into a shared spatial view and a distributed GPU training system to scale workloads across multiple graphics processors. The toolkit covers several capability areas,

graph_nets is a graph-structured deep learning framework and library for building message-passing neural networks. It provides tools for designing architectures that operate on nodes and edges to process and reason about data structured as graphs using TensorFlow. The framework implements a message-passing paradigm for iterative information exchange between nodes. This approach enables the development of models that can reason about complex graph-structured inputs for tasks such as path-finding and sorting, or serve as a predictor for the future states and trajectories of physical systems.

Open3D is a 3D data processing library, visualization engine, and machine learning library. It provides a framework for manipulating point clouds and meshes through specialized algorithms designed for 3D data science workflows. The project includes a toolkit for 3D scene reconstruction to generate spatial models and align surfaces from raw data. It also functions as a GPU accelerated framework that offloads intensive spatial computations to the graphics processor to increase processing speed. The library covers a broad range of capabilities including physically based light simulations for vi

Sapiens is a high-resolution human vision model designed for high-precision, human-centric computer vision tasks. It functions as a suite of tools for estimating human pose, depth, and surface geometry. The project utilizes a vision transformer backbone to perform multiple tasks through a shared encoder. This architecture enables the simultaneous prediction of skeletal structures, joint locations, and the distance between a camera and a human subject. The model's capabilities cover human body part segmentation to isolate anatomical regions from backgrounds and surface normal prediction to re

Potree is a web-based point cloud rendering engine and viewer designed for the visualization and analysis of massive 3D spatial datasets and LIDAR scans. It functions as a geospatial analysis tool that enables the interactive exploration of high-density point clouds directly within a web browser using WebGL. The system utilizes eye-dome lighting to enhance depth perception of 3D structures and supports virtual reality for immersive spatial exploration. It provides specialized capabilities for 3D scene documentation through hierarchical annotations and the creation of animated camera fly-throu

cuml is a GPU-accelerated machine learning library and framework that uses CUDA to accelerate tabular data preprocessing and model execution. It provides a suite of tools for training and deploying classification, regression, and clustering models on NVIDIA GPUs and GPU clusters. The library is designed for scalability, offering a distributed GPU machine learning environment that can spread computation and data across multiple hardware accelerators and nodes to handle datasets exceeding single-device memory. It mirrors standard estimator interfaces to allow the replacement of CPU-based models

hnswlib is a header-only C++ library and vector indexing engine designed for high-dimensional approximate nearest neighbor search. It organizes large collections of embeddings into a searchable graph structure to enable rapid proximity queries and distance calculations. The system utilizes Hierarchical Navigable Small World graphs to achieve fast vector similarity search. It distinguishes itself by allowing the definition of custom distance metrics and similarity functions to adapt calculations to specific data requirements. The engine covers the full indexing lifecycle, including incrementa