linlin's repositories
Awesome-Talking-Face
📖 A curated list of resources dedicated to talking face.
3DDFA-V3-opencv-dnn
使用opencv部署3D人脸重建3DDFA-V3，包含C++和Python两个版本的程序，只依赖opencv库就能运行
blender_livelinkface
Stream/load ARKit blendshapes from LiveLinkFace direct to Blender
BVH2SMPL
I love human motion retargeting.
chatgpt-on-wechat
基于大模型搭建的微信聊天机器人，同时支持微信、企业微信、公众号、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/GLM-4/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。
CiteTracker
[ICCV'23] CiteTracker: Correlating Image and Text for Visual Tracking
denoising-diffusion-pytorch
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
DPVO
Deep Patch Visual Odometry/SLAM
Esp32_VoiceChat_LLMs
esp32 based device, mainly used for voice chat with large language models
FEARTracker
Official repo for FEAR: Fast, Efficient, Accurate and Robust Visual Tracker (ECCV 2022)
freemocap
Free Motion Capture for Everyone 💀✨
godmodeanimation
2D Game Animation in God Mode
hold
[CVPR 2024 Highlight] This is a repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D hand-object training data.
HoT
[CVPR 2024 🔥] Official implementation of the paper "⏳ Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation"
humanplus
HumanPlus: Humanoid Shadowing and Imitation from Humans
InternVL
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源模型
live_mocap
Single-view real-time motion capture built up upon Google Mediapipe.
LivePortrait
Bring portraits to life!
ModernRobotics
Modern Robotics: Mechanics, Planning, and Control Code Library --- The primary purpose of the provided software is to be easy to read and educational, reinforcing the concepts in the book. The code is optimized neither for efficiency nor robustness.
OpenRoboExp
This project is dedicated to advancing the field of animatronic robots by enabling them to generate lifelike facial expressions, pushing the boundaries of what's possible in human-robot interaction.
rtmlib
RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
Single_Object_Tracking_Paper_List
Paper list for single object tracking (State-of-the-art SOT trackers)
SPARK
Official implementation for the SIGGRAPH Asia 2024 paper SPARK: Self-supervised Personalized Real-time Monocular Face Capture
Streamer-Sales
Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️