awesome-avatars
github.com/pansanity666/awesome-avatars ↗List of recent advances for human avatars, including generation, reconstruction, and editing, etc.
276
GitHub Stars
75
Curated Resources
10
Categories
3 hours ago
Last Refreshed
Avatar GenerationPer-subject Avatar ReconstructionGeneralizable Avatar Novel View SynthesisGeneralizable Avatar Mesh ReconstructionText-to-AvatarAvatar InteractionMotion GenerationSMPL EstimationDatasetAknowledgement
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me avatar generation resources from awesome-avatars"
Installation instructions →What's inside
Avatar Generation
- 3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective.
- AG3D: Learning to Generate 3D Avatars from 2D Image Collections
- AvatarGen: a 3D Generative Model for Animatable Human Avatars
- EVA3D: Compositional 3D Human Generation from 2D Image Collections
- GENERATIVE NEURAL ARTICULATED RADIANCE FIELDS
- Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors.
Generalizable Avatar Novel View Synthesis
- ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs
- GHuNeRF: Generalizable Human NeRF from a Monocular Video
- GP-NeRF: Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering
- GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
- HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs
- MonoNHR: Monocular Neural Human Renderer
Text-to-Avatar
- Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
- AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation
- AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars
- AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control
- AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion
- AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose
Aknowledgement
SMPL Estimation
- CLIFF: Carrying location information in full frames into human pose and shape estimation
- D&d: Learning human dynamics from dynamic camera
- End-to-end human pose and mesh reconstruction with transformers.
- GLAMR: Global occlusion-aware human mesh recovery with dynamic cameras
- Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation
- Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation
Dataset
Generalizable Avatar Mesh Reconstruction
- Complete 3D Human Reconstruction from a Single Incomplete Image
- DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction
- D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
- ECON: Explicit Clothed humans Optimized via Normal integration
- Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
- High-fidelity 3D Human Digitization from Single 2K Resolution Images
Showing a sample of 75 resources. View the full list on GitHub →