6 个仓库
Awesome GitHub RepositoriesHead Pose Estimation
Techniques for calculating the 3D orientation and position of a head relative to a camera.
Distinct from 3D Pose Estimation: Distinct from 3D Pose Estimation: specifically targets the orientation of the head rather than full body or generic object pose.
Explore 6 awesome GitHub repositories matching artificial intelligence & ml · Head Pose Estimation. Refine with filters or upvote what's useful.
Awesome Head Pose Estimation GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- tadasbaltrusaitis/openface
TadasBaltrusaitis/OpenFace
7,690在 GitHub 上查看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。
Calculates the orientation and position of a head in 3D space relative to the camera.
MATLAB - yadiraf/prnet
YadiraF/PRNet
5,013在 GitHub 上查看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。
Implements techniques for calculating the 3D orientation and position of a head relative to a camera.
Python - zejun-yang/aniportrait
Zejun-Yang/AniPortrait
5,020在 GitHub 上查看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。
Directs specific head orientation and movement during animation using external control files.
Python - xlite-dev/lite.ai.toolkit
xlite-dev/lite.ai.toolkit
4,413在 GitHub 上查看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。
Calculates 3D head orientation using yaw, pitch, and roll Euler angles.
C++ - cleardusk/3ddfa
cleardusk/3DDFA
3,678在 GitHub 上查看3DDFA is a 3D face reconstruction tool that generates three-dimensional facial meshes and 68 structural landmarks from a single two-dimensional input image. The project provides utilities for estimating facial pose and depth maps to determine the orientation and position of a face. It includes a geometry exporter to save reconstructed facial shapes into standard file formats for use in external 3D modeling software. The software further covers automated face cropping using landmark-based and landmark-free identification methods, as well as the extraction of specialized mathematical represent
Calculates the 3D orientation and position of the head to ensure consistent facial reconstruction.
Python - yinguobing/head-pose-estimation
yinguobing/head-pose-estimation
1,351在 GitHub 上查看This project is a computer vision tool designed to calculate the pitch, yaw, and roll of a human head in real time. It functions as a facial landmark detection library that identifies sixty-eight specific points on a face to enable precise orientation tracking from video streams. The system utilizes a high-performance inference engine to execute pre-trained machine learning models, ensuring that geometric analysis is performed efficiently on input frames. By mapping detected facial coordinates to a three-dimensional model, the software determines the camera-relative rotation of the head throu
Calculates the pitch, yaw, and roll of a human head using facial landmarks and perspective algorithms.
Pythonconvolutional-neural-networksdeep-learningfacial-landmarks-detection
