Awesome GitHub Repositories3D Pose Estimation

SadTalker is a generative framework designed to synthesize expressive talking head videos from static portrait images. By mapping audio signals or text prompts to three-dimensional facial motion coefficients, the system synchronizes lip movements, facial expressions, and head orientation to create realistic digital character performances. The project distinguishes itself by decoupling identity from dynamic motion through latent space encoding, ensuring that the generated animations maintain visual fidelity to the source portrait. It supports comprehensive motion synthesis, including full-body

AlphaPose 是一个深度学习姿态估计框架和 PyTorch 计算机视觉库，旨在检测和追踪图像及视频中的人体、面部、手部和足部关键点。它提供了一套用于骨骼姿态估计和多人姿态追踪的系统。 该项目实现了三维人体姿态重建工具，可从二维图像数据生成关节位置和人体网格形状。它还包含一个多人姿态追踪器，能够在连续的视频帧中保持多人的身份识别。 该框架涵盖了广泛的计算机视觉功能，包括多人关键点定位、人体运动追踪以及三维人体网格重建。

OpenFace 是一个情感计算框架和面部行为分析工具包，旨在提取面部特征并识别肌肉运动，从而分析人类的情感行为。它为通过计算机视觉分析人类情感和社会互动模式提供了一个研究平台。 该软件实现了一套工具，用于检测面部关键点、计算相对于摄像头的 3D 头部姿态，并通过分析眼睛位置和方向来追踪视线。它还包括面部动作单元识别功能，以识别特定的肌肉运动。 该项目涵盖了广泛的面部分析原语，包括将原始图像处理为对齐人脸和标准化描述符的面部特征提取。

MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D keypoints on humans, animals, and faces. It serves as a computer vision model zoo and a framework for both 2D pose estimation and 3D pose lifting. The project is distinguished by its modular architecture and extensibility, employing a registry-based system and hierarchical configurations to allow for custom algorithm integration and model pipeline customization. It supports diverse estimation paradigms, including top-down, bottom-up, and two-stage pose lifting workflows. The

DensePose is a 3D human pose estimation framework designed to map 2D image pixels to a 3D surface-based model of the human body in real time. It functions as a computer vision anatomical mapper that projects 2D visual data onto a 3D surface to create detailed anatomical representations. The system operates as an image-to-3D texture transfer engine, localizing 2D image annotations onto 3D models to apply photographic textures to digital human representations. It uses a surface-based body mapping method to associate human pixels in an RGB image with specific coordinates on a 3D body template.

Relativ is an open-source project for the development of custom virtual reality hardware, encompassing the mechanical design, electronics, and software interfaces required to build a headset from scratch. It provides the frameworks necessary for assembling devices using open-source electronics and firmware. The project integrates custom hardware with SteamVR through driver-based configurations, mapping device identifiers and display viewports to ensure rendered images align with physical secondary displays. It employs a combination of microcontroller-based inertial measurement unit polling fo

OpenCVSharp is a .NET library that wraps native OpenCV functions, providing C# developers with access to OpenCV's computer vision capabilities through an API that mirrors the native C/C++ style. It serves as a managed wrapper for image processing, feature detection, object detection, and image manipulation tasks, while also handling automatic disposal of unmanaged OpenCV resources like Mat objects to prevent memory leaks in .NET applications. The library enables keypoint detection and descriptor extraction using algorithms such as AKAZE, BRISK, or FAST, with brute-force or FLANN-based matchin

SAM 3D Objects is a promptable foundation model that recovers 3D objects and human meshes from single images. It converts masked objects in a single photograph into full 3D models with pose, shape, texture, and layout, while also producing complete 3D human body meshes from the same input. The system integrates promptable segmentation to isolate objects and humans before reconstruction, then aligns the independently reconstructed 3D elements into a shared coordinate space. This enables scene-level understanding where multiple 3D reconstructions from the same image coexist in a common coordina

DeepLabCut 是一个用于无标记 2D 和 3D 动物姿态估计的深度学习工具包。它作为一个运动跟踪系统，无需物理标记即可识别视频序列中动物的解剖关键点。 该框架利用迁移学习和预训练权重库来加速针对不同物种的网络训练。它支持多体身份跟踪以在视频序列中保持唯一身份，并提供用于实时视频流的姿态检测功能。 该系统涵盖了广泛的计算机视觉功能，包括 3D 空间运动分析、解剖标记跟踪和自监督预测细化。它包括用于训练数据标注的实用程序，以及用于集成自定义神经网络架构的模型注册表。 该软件提供 Docker 容器化，以确保在不同操作系统上的一致安装和执行。

Kalidokit is a web-based motion capture tool that transforms real-time webcam video into 3D character animation data. It functions as a blendshape and kinematics calculator, converting facial, hand, and body tracking data from Mediapipe and TensorFlow.js into blendshape weights and euler rotations for driving digital puppets and avatars. The tool solves face landmarks to derive head rotation, eye blinks, mouth shapes, and brow values for rigging, while hand landmarks are converted into finger joint rotations and body keypoints into per-joint euler rotations for full-body animation. It include

PRNet 是一个用于 3D 人脸重建的 Python 库。它使用深度学习回归模型，从单张 2D 输入图像预测 3D 人脸几何结构和顶点颜色，从而生成带纹理的网格模型。 该项目提供了数字换脸工具，允许将目标人脸替换为新图像，并混合纹理以匹配原始姿态。它还包含一个用于人脸纹理交换和混合以适应特定 3D 姿态的框架。 其他能力涵盖了人脸分析，包括人脸关键点的检测与对齐，以及头部姿态和相机方向矩阵的估计。

AniPortrait 是一个 AI 视频合成流水线，旨在生成照片级逼真的说话肖像和面部动画。它充当说话头像生成器和音频驱动的动画师，将唇部动作、表情和头部姿势与语音或参考视频源同步。 该系统包括一个面部表情迁移工具，用于将源视频中的动作重演到静态参考图像上。它利用带有参考图像调节的潜在扩散模型，在生成的帧中保持视觉身份和一致性。 该流水线涵盖音频到表情的映射、姿势引导的运动控制和照片级逼真的视频合成。它结合了帧插值上采样，以加速生成过程并减少总渲染时间。

这是一个面向 .NET 生态系统的科学计算框架，提供了一套全面的数值分析、统计和数学优化库。它作为开发机器学习、数字信号处理和计算机视觉应用的基础工具包。 该框架提供了用于训练和部署预测模型的专用工具包，包括神经网络、支持向量机和决策树。它还通过对实时视觉分析（如对象跟踪和面部特征检测）的深度集成，以及用于捕获和过滤音频及传感器信号的专用数字信号处理库而脱颖而出。 其功能范围扩展到高级矩阵分解和线性代数、概率状态建模和启发式搜索算法。它还涵盖了广泛的数据操作实用程序，从降维和归一化到空间数据组织和科学可视化组件。 该系统包括用于摄像机配置、GPIO 端口管理和专用深度传感硬件的硬件集成控制器。

GET3D is a generative 3D mesh model and rendering framework designed to synthesize high-quality textured shapes and tetrahedral meshes. It functions as an image-to-3D reconstructor and text-to-3D generator, utilizing a differentiable 3D renderer to produce realistic visual perspectives and material effects. The system enables the creation of 3D assets from single 2D images, point clouds, or descriptive text prompts. It features a latent space interpolator for creating smooth transitions between different 3D objects and supports the independent control of geometry and texture. The project cov

EasyMocap is a markerless 3D human motion capture system that recovers body, hand, and face poses from single or multi-view video without physical markers or suits. It uses parametric body models like SMPL, SMPL-X, and MANO, and leverages mirror reflections to resolve depth ambiguity in single-view pose estimation, improving accuracy by computing mirror surface normals from vanishing points. The system distinguishes itself through mirror-assisted depth disambiguation, enabling accurate 3D pose reconstruction from a single RGB image or video that includes a mirror reflection. It also supports

lite.ai.toolkit 是一个专为边缘 AI 部署设计的 C++ 计算机视觉工具包。它支持在资源受限的设备上执行用于目标检测、图像分类和分割的预训练模型。 该项目具有支持 ONNX 模型运行时的多后端推理引擎，允许 AI 模型跨不同的硬件目标运行。它包含一个专门针对 NVIDIA 硬件的 GPU 加速管道，以减少延迟并提高处理速度。 该工具包涵盖了广泛的面部分析功能，包括情绪检测、性别和年龄估计以及头部姿态分析。它还通过提取特征嵌入和计算余弦相似度来验证身份，从而提供面部识别工具。 其他功能包括用于前景隔离的图像抠图、灰度图像着色和艺术风格迁移。

Depth-Anything-3 is a collection of core model implementations for depth prediction, multi-view geometry estimation, and RGB-D spatial pipelines. It includes a monocular depth estimation model for predicting depth maps from single images or video, and a 3D Gaussian splatting generator that predicts parameters to synthesize high-fidelity novel views of a scene. The project provides a multi-view geometry estimator for calculating spatially consistent depth and camera poses across synchronized visual inputs. It also functions as a visual SLAM enhancement tool designed to reduce drift and improve

evo 是一个用于评估 SLAM 算法、机器人里程计和轨迹数据的 Python 框架。它作为一个分析库，通过计算估计路径与真值参考之间的绝对和相对位姿误差来测量漂移和精度。 该项目提供了一个几何对齐框架，用于校正空间轨迹之间的旋转、平移和缩放，确保误差测量的一致性。它包含用于里程计漂移分析和机器人数据处理的专业工具，包括从 ROS bagfiles 中提取轨迹信息的能力。 该软件涵盖了广泛的功能，包括支持地理地图瓦片和 ROS 地图叠加的 2D 和 3D 轨迹可视化。其他功能包括时间戳同步、空间变换以及过滤或导出各种行业标准格式轨迹数据的能力。

VideoPose3D is a machine learning framework designed for 3D human pose estimation. It functions as a motion reconstruction tool that predicts 3D joint positions from 2D video sequences using a temporal convolutional network to process body movement over time. The project includes a semi-supervised learning pipeline that improves pose accuracy by combining labeled datasets with unlabeled video data and projection consistency loss. It also features a video pose visualizer capable of rendering 3D skeleton reconstructions and 2D keypoints as overlays on original footage. The framework covers the

This project is a 3D visual localization framework designed to determine a camera's exact position and orientation by matching 2D image features against a 3D reference model. It includes a structure-from-motion pipeline to reconstruct 3D scene geometry from unordered image sets, creating the necessary spatial maps for localization. The system employs a hierarchical coarse-to-fine localization approach. This process begins with a global-descriptor image retrieval system to identify candidate reference images from a large database and progresses through local feature matching to final 3D model