Awesome GitHub RepositoriesPoint Cloud

The Intel RealSense SDK is a software development kit providing drivers and libraries for interfacing with depth cameras to capture color, depth, and infrared data streams. It includes a depth camera driver for device discovery and sensor configuration, a stereo vision library for computing depth maps and aligning frames, and a 3D point cloud generator to transform depth and infrared frames into spatial representations. The SDK distinguishes itself through on-chip depth calculation and stereo calibration, using internal vision processors to reduce host CPU load. It supports hardware-level str

Draco is a library and toolset for compressing, transcoding, and decoding 3D geometric meshes and point cloud data. Its primary purpose is to reduce storage size and transmission bandwidth for 3D assets. The project includes a geometry optimizer specifically for glTF file containers to reduce asset footprints. It also features a hardened decoder designed to process malformed or untrusted 3D geometric data safely to prevent memory corruption and crashes. The software covers a broad range of 3D data processing capabilities, including geometric data reconstruction, point attribute management, a

mmcv is a foundation library for computer vision based on PyTorch. It provides a comprehensive system for constructing convolutional neural networks, a toolkit for image and video preprocessing, and a collection of high-performance deep learning vision operators. The project is distinguished by its hardware-accelerated kernels for complex operations such as deformable convolutions and region pooling. It features a configuration-driven framework that allows for the dynamic instantiation of network layers and the registration of custom modules without modifying code. The library covers a broad

MMDetection3D is an open-source toolbox for 3D perception, providing a unified framework for detecting and segmenting objects in three-dimensional environments. It supports a range of core tasks including monocular 3D object detection from single camera images, LiDAR-based 3D object detection from raw point clouds, and multi-modal fusion that combines camera images with LiDAR data. The toolbox also covers point cloud semantic segmentation, assigning class labels to every point in a scan for scene understanding. The project distinguishes itself through a config-driven pipeline that orchestrate

Potree 是一个基于 Web 的点云渲染引擎和查看器，专为大规模 3D 空间数据集和 LIDAR 扫描的可视化与分析而设计。它作为一种地理空间分析工具，支持使用 WebGL 直接在 Web 浏览器中对高密度点云进行交互式探索。 该系统利用眼穹照明（eye-dome lighting）增强 3D 结构的深度感知，并支持虚拟现实以进行沉浸式空间探索。它通过分层注释和创建动画相机漫游导览，为 3D 场景文档提供专业功能。 该平台包括地理空间数据分析工具，如空间距离和面积测量、高程剖面分析，以及外部 shapefile 和 geopackage 的叠加。用户可以使用基于属性的过滤和裁剪体积隔离来提取特定特征，同时外部图像可以与点云视角对齐和同步。 Potree 采用预处理的二进制格式和基于八叉树的空间索引，以促进大规模数据集的异步数据流传输和细节层次（LOD）渲染。

Tixl 是一个基于节点的动态图形引擎和程序化生成工具，用于创建 3D 几何体和着色器。它利用有向无环图（DAG）操作符和 GPU 加速计算内核来生成复杂的 3D 形状，特别是通过使用符号距离函数（SDF）和粒子模拟。 该引擎通过 C# 开发框架具有高度可扩展性，支持热代码重载，允许在不重启的情况下将自定义操作符逻辑注入到活动运行时中。它还作为一个灯光控制器脱颖而出，能够将 3D 空间属性和旋转转换为 DMX 和 ArtNet 协议，以驱动物理舞台设备。 该平台涵盖了广泛的能力，包括通过 FFT 分析实现的音频响应可视化、关键帧和程序化动画，以及通过 MIDI 和 OSC 集成的实时外部控制。其渲染流水线支持基于物理的渲染（PBR）和自定义着色器构建，同时该环境还提供了用于投影映射和独立可执行文件部署的工具。 该项目提供了一个用于构建应用程序的 CLI 和一个用于创建 C# 扩展的开发界面。

Muzic 是一个用于 AI 驱动的音乐分析、创作和合成的深度学习平台和框架。它作为一个音乐生成框架和分析工具，利用大型语言模型和自主智能体来编排符号音乐和音频音乐的创作与解读。 该项目以其跨模态能力而著称，将自然语言和符号音乐映射到共享的联合嵌入空间中，用于零样本分类和信息检索。它采用了多种专门的架构，包括用于音频合成的扩散框架、用于长序列结构一致性的双粒度注意力机制，以及结合音乐理论规则与神经网络的混合系统。 该平台涵盖了广泛的功能，包括从文本和歌词生成 MIDI 序列、神经歌声合成以及自动歌词转录。它还提供用于音乐结构建模、基于属性的符号生成以及通过自主智能体编排外部音乐工具的工具。 支持性实用程序包括用于大规模 MIDI 二进制化、数据集编码的数据工程流水线，以及用于旋律音符提取和语音到音素对齐的音频信号处理。

该项目是一个基于 PyTorch 的深度学习模型框架，专为 3D 点云数据的分类和语义分割而设计。它提供了 PointNet 架构的实现，用于执行整个对象的全局类别标注以及大规模 3D 环境的详细分区。 该系统处理跨多个尺度的语义分割，范围从识别单个对象内的组件到标注大规模场景中的不同类别类型。 该框架包括用于处理无序点集的结构化组件，例如最远点采样、层级点集分组和对称集聚合网络。它还提供离线数据预处理工具，以及用于在外部软件中可视化分割输出的 3D 对象文件生成工具。

CloudCompare 是一款用于处理和分析 3D 点云和多边形网格的专业软件。它作为一个 3D 网格分析工具和大型数据集可视化工具，旨在在 3D 环境中显示和管理数百万个点。 该软件提供点云比较的专业功能，利用优化的八叉树结构计算两个 3D 数据集之间的空间差异。这使得识别点云之间或点云与网格之间的变化和误差成为可能。 该系统涵盖了广泛的 3D 数据分析领域，包括大规模点云的处理和 3D 网格的几何评估。它通过内存高效的处理和针对海量数据集的专业渲染来保持高性能。

PointNet++ is a deep learning framework designed for processing and classifying 3D point cloud data. It utilizes a hierarchical feature learning architecture to extract geometric patterns from sampled 3D point sets. The framework implements a variety of 3D analysis tools, including a point cloud classifier for categorizing objects based on spatial coordinates and surface normals, a semantic scene segmenter for labeling surfaces in large-scale environments, and a tool for 3D object part segmentation. The system covers a broad range of capabilities including geometric feature extraction, 3D da

This is a structured deep learning curriculum for programmers, delivered as a collection of Jupyter notebooks. It teaches the fundamentals of training neural networks for computer vision, natural language processing, tabular data analysis, and collaborative filtering using PyTorch and the fastai library. The course is designed to be hands-on, guiding learners from building a training loop from scratch to fine-tuning pretrained models for a variety of practical tasks. The curriculum distinguishes itself by covering the full lifecycle of a deep learning project, from data preparation and augmen

A C++ & Python viewer for 3D data like meshes and point clouds

Point cloud importer & renderer for Unity

Entwine - point cloud organization for massive datasets

VeloView performs real-time visualization and easy processing of live captured 3D LiDAR data from Velodyne sensors (Alpha Prime™, Puck™, Ultra Puck™, Puck Hi-Res™, Alpha Puck™, Puck LITE™, HDL-32, HDL-64E). Runs on Windows, Linux and MacOS. This repository is a mirror of https://gitlab.kitware.com/LidarView/VeloView-Velodyne.

LidarView performs real-time reception, recording, visualization and processing of 3D LiDAR data. This repository is a mirror of https://gitlab.kitware.com/LidarView/lidarview.

Visualise your data in virtual reality with ImmersivePoints