Projects sharing features with Open3D

OpenPCDet is a PyTorch deep learning library and toolbox for LiDAR 3D object detection. It functions as a point cloud processing framework designed to develop, train, and evaluate machine learning models that identify and locate objects in three dimensional space. The project includes a GPU-accelerated geometry engine for high-performance implementation of 3D intersection over union and rotated non-maximum suppression. It also provides a distributed model training tool to scale the training and testing of detection models across multiple GPUs and computing nodes. The framework covers point c

World's first general purpose 3D object detection codebse.

efficient tools for LiDAR processing

Kaolin is a PyTorch 3D deep learning library providing a comprehensive suite of tools for 3D geometry processing, physics simulation, data visualization, and gradient-based rendering for computer vision. The library includes a differentiable 3D renderer and a geometry processing toolkit for converting and transforming 3D representations such as meshes and point clouds. It also features a 3D physics simulation engine to calculate physical interactions and collisions between three-dimensional objects and scenes. The toolkit provides utilities for 3D data visualization, including the creation o

Open3D is a software toolkit designed for the processing, alignment, and reconstruction of three-dimensional data. It functions as a computer vision geometry engine that enables the manipulation of point clouds, meshes, and volumetric grids derived from sensor inputs. The library distinguishes itself through a high-performance computational core that executes geometric processing tasks in native code, paired with a binding layer that exposes these capabilities to high-level languages for rapid prototyping. It provides specialized algorithms for spatial registration, allowing users to merge mu

Blender is a professional 3D creation suite designed for modeling, animation, rendering, and video editing. It functions as an open-source 3D engine that provides a comprehensive framework for procedural geometry, physics simulation, and high-quality visual output. The platform is built upon a foundational architecture that utilizes data-block-based memory management and a dependency-graph-based evaluation system to handle complex scene transformations and geometry updates. The software distinguishes itself through a highly modular, node-based procedural architecture that allows users to cons

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

openMVG is a computer vision geometry library and toolkit for multiple view geometry. It serves as a framework for structure from motion and 3D scene reconstruction, providing the tools necessary to recover 3D point clouds and camera poses from collections of 2D images. The library implements both global and incremental structure-from-motion pipelines. It uses geometric algorithms to calculate camera pose estimation and image localization, employing Levenberg-Marquardt bundle adjustment to refine 3D coordinates and camera parameters by minimizing reprojection error. The project covers a broa

ECharts is a JavaScript data visualization library and web charting framework used to render interactive 2D and 3D data plots within a web browser. It functions as a visualization engine that transforms raw data into customizable charts and graphs. The project includes a WebGL-based hardware acceleration engine specifically for producing three-dimensional plots and globe visualizations. This allows the library to handle large and complex datasets through GPU-accelerated rendering. The framework supports both canvas-based raster rendering and SVG-based vector rendering. It provides capabiliti

CuPy is a CUDA array computing library that implements a NumPy-compatible interface for executing array operations and numerical computing on NVIDIA GPUs. It serves as a GPU-accelerated numerical library and a CUDA-based SciPy implementation, offloading heavy calculations to graphics hardware to increase processing speed for scientific and engineering workloads. The library enables multi-framework tensor exchange, allowing data buffers to be shared between different deep learning frameworks using standardized memory layouts to avoid memory copies. It also supports custom GPU kernel integratio

This project is a PyTorch-based framework of deep learning models designed for the classification and semantic segmentation of 3D point cloud data. It provides implementations of the PointNet architecture to perform global category labeling of entire objects and detailed partitioning of large-scale 3D environments. The system handles semantic segmentation across multiple scales, ranging from identifying individual components within a single object to labeling distinct category types within large-scale scenes. The framework includes structural components for processing unordered point sets, s

Hashcat is a high-performance hash cracking software and OpenCL compute application used to recover plain-text passwords from hashed data. It functions as a GPU-accelerated recovery tool and distributed password cracker, leveraging CPUs and GPUs to perform intensive cryptographic computations. The system differentiates itself through a distributed cracking workflow that coordinates tasks across multiple machines via an overlay network to share computational load. It further optimizes recovery speed using Markov chain keyspace optimization to prioritize the most likely password candidates. Th

Skia is a high-performance 2D graphics rendering library used for drawing text, geometries, and images on digital surfaces. It functions as a hardware-accelerated graphics engine that offloads drawing operations to the GPU, a vector graphics processor for SVG and complex paths, and a typography engine for shaping and drawing characters with Unicode support. The project provides a cross-platform image codec for encoding and decoding standard image formats into raw pixel data across multiple operating systems. It also enables the development of user interfaces that maintain visual consistency a

wslg is an integration layer and display server system designed to run Linux graphical applications on Windows. It provides a bridge between Linux window management, audio routing, and system clipboards and the Windows host, utilizing a Wayland and X11 display server to support visual software. The system utilizes a virtual GPU architecture to provide hardware-accelerated rendering for graphics-intensive applications. It implements a Remote Desktop Protocol gateway to stream graphical frames and uses a specialized sound server interface to route audio and microphone data between the Linux gue

Darknet is a low-level neural network engine and framework written in C. It is designed for training and deploying deep learning models, with a primary focus on convolutional neural networks. The project serves as a CUDA accelerated deep learning library that offloads heavy mathematical operations to NVIDIA graphics hardware. This acceleration is used to increase processing speed and reduce execution time during the training of large networks. The engine supports a range of activities including deep learning research, image recognition development, and the training of convolutional neural ne

Bend is a high-level parallel programming language and compiler designed to execute code across multi-core CPUs and GPUs automatically. By translating functional source code into a graph-based intermediate representation, it enables massive parallel execution without requiring manual management of threads, locks, or atomic operations. The runtime operates as an interaction net engine, where computations are represented as networks of nodes that reduce through local rewriting rules. This model utilizes a work-stealing scheduler to distribute tasks across thousands of hardware threads, ensuring

Taskflow is a C++ task-parallel framework designed to build high-performance parallel workflows and complex dependency graphs. It provides a programming model that organizes computational work into directed acyclic graphs, enabling developers to manage concurrency, resource scheduling, and task dependencies across multi-core CPUs and GPU accelerators. The framework distinguishes itself through its ability to orchestrate heterogeneous systems, allowing for the integration of hardware-accelerated kernels and memory operations into unified execution pipelines. It supports dynamic runtime subflow

Numba is a just-in-time compiler that translates high-level Python functions into optimized machine code at runtime. By leveraging the LLVM compiler infrastructure, it provides a framework for accelerating numerical data processing and mathematical computations, enabling performance levels comparable to statically compiled languages. The project distinguishes itself through its ability to perform type-inference-based specialization, which generates machine instructions tailored to the specific data types used during execution. It employs a lazy compilation pipeline that defers translation unt

3DV 2021 Oral Sceneformer: Indoor Scene Generation with Transformers: Generate indoor scenes with Transformers

By Chen Liu, Kihwan Kim, Jinwei Gu, Yasutaka Furukawa, and Jan Kautz

official source code of paper 'IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo'

This is an official implementation for PlaneRecNet: A multi-task convolutional neural network provides instance segmentation for piece-wise planes and monocular depth estimation, and focus on the cross-task consistency between two branches. 22th. Oct. 2021: Initial update, some trained models…

3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.

Benjamin Graham, David Novotny 3DV 2020

ICCV'21 PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

CGAL is a software library that provides a comprehensive collection of computational geometry algorithms and data structures. It is built around a geometry kernel that defines fundamental geometric primitives and operations, enabling the construction of complex geometric objects and the computation of geometric predicates with exact arithmetic for reliable results. The library covers a wide range of geometric computation capabilities, including the construction of convex hulls, triangulations of point sets, and the generation of Voronoi diagrams. It also supports the processing of polygonal m