Pinned Repositories
Ask-Anything
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
3Dface_pca
一种高自由度的捏脸方法：使用PRNet获取任意想要获取的人脸数据（可用于数据分析或作为捏脸的数据基），pca分析人脸3D模型顶点以及纹理，得出主成分向量，控制主成分向量与人脸模型相加，可分别捏人脸轮廓以及人脸纹理。
DensePose
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
hmr
Project page for End-to-end Recovery of Human Shape and Pose
openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
semantic_human_texture_stitching
This repository contains texture stitching code corresponding to the paper Detailed Human Avatars from Monocular Video.
vilbert-multi-task
Multi Task Vision and Language
snowyrain's Repositories
snowyrain/3Dface_pca
一种高自由度的捏脸方法：使用PRNet获取任意想要获取的人脸数据（可用于数据分析或作为捏脸的数据基），pca分析人脸3D模型顶点以及纹理，得出主成分向量，控制主成分向量与人脸模型相加，可分别捏人脸轮廓以及人脸纹理。
snowyrain/DensePose
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
snowyrain/hmr
Project page for End-to-end Recovery of Human Shape and Pose
snowyrain/openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
snowyrain/semantic_human_texture_stitching
This repository contains texture stitching code corresponding to the paper Detailed Human Avatars from Monocular Video.
snowyrain/vilbert-multi-task
Multi Task Vision and Language