A monorepo providing `@pixiv/three-vrm`, a library for loading, controlling, and rendering VRM (Virtual Reality Model) avatars in three.js. It implements VRM 1.0 and partial VRM 0.0 specifications, handling humanoid bone mapping, facial expressions, eye gaze control (lookAt), first-person mesh culling, spring bone physics simulation, node constraints (aim, roll, rotation), and MToon toon material rendering. The library is structured as a collection of GLTFLoader plugins that parse VRM extensions from `.vrm` files. Core modules include `VRMLoaderPlugin` (orchestrating sub-plugins), `VRMCore` (humanoid, expressions, lookAt, firstPerson), `VRMSpringBoneManager` (verlet physics), `VRMNodeConstraintManager` (topological sort for constraints), and `MToonMaterial`/`MToonNodeMaterial` (custom shader/material for toon rendering). Both WebGL and experimental WebGPU renderers are supported. The codebase includes thorough examples, CI/CD, and compatibility shims for multiple three.js revisions (r123 through r180).
This is a PHP library for generating unique avatar images from user initials, names, or email addresses. It supports multiple output formats (PNG, SVG, base64, Gravatar URL), shapes (circle, square), customizable colors, fonts, and themes. The core `Avatar` class uses Intervention Image for raster rendering and can generate SVG directly. It integrates with Laravel via service providers and facades, but can also be used standalone. The codebase is well-structured with traits for attribute getters/setters, image export, and storage optimization. The library is actively maintained, supports PHP 8.3+, and follows modern PHP practices. Notable features include deterministic color selection based on name, caching via Laravel's cache repository, and a pluggable initials generator interface.
LiveTalking is a real-time interactive streaming digital human engine that synchronizes lip movements with audio generated from text or speech input. It functions as a production-grade web server (Flask + aiohttp) supporting WebRTC, RTMP, and virtual camera output, enabling applications like live streaming, virtual assistants, and conversational avatars. The system integrates a pluggable pipeline: user input → optional LLM (OpenAI-compatible) → TTS (8+ providers including EdgeTTS, CosyVoice, GPT-SoVITS) → lip-sync model inference (Wav2Lip, MuseTalk, Ultralight Digital Human) → video frame compositing → streaming output. It also includes ASR via a local FunASR/SenseVoice WebSocket server and a web admin UI for session management and avatar generation. Architecturally, it follows a plugin-based design using a decorator registry (registry.py) that allows extending TTS, Avatar, and Output modules via registration. The core rendering loop in BaseAvatar manages three concurrent threads (TTS, inference, frame processing) with queue-based data flow. WebRTC integration uses aiortc for peer connections, and the system supports multi-session concurrency with session limits. While primarily an application, it embeds research-derived model code (Whisper, face detection, face parsing) and includes a benchmark script for ASR latency comparison. The codebase has some technical debt: duplicated face detection utilities, stale Dockerfile (Python 3.10/torch 1.12 vs README's newer requirements), and commented-out legacy code. However, the core architecture is solid, and the plugin system and audio utilities are well-crafted and reusable.
This repository is a curated awesome-list of research papers, projects, datasets, and industry demos related to digital humans: 3D avatar generation and animation, clothed human reconstruction, head avatars, human motion generation, virtual try-on, cloth simulation, and related topics. It contains only a README.md plus LICENSE; there is no application code, no executable pipeline, no tests, no CI, and no dependency manifests. Despite the data_research classification, it is best understood as a manually maintained literature index rather than a data pipeline or software project.