SizheAn/PanoHead

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1956 stars · 236 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

PanoHead is the official PyTorch implementation of a CVPR 2023 paper presenting a 3D-aware GAN that synthesizes geometry-aware, view-consistent full human heads in 360 degrees from in-the-wild images. It also supports reconstructing personalized 3D head avatars from a single input photo.

Use cases

• generate 3d consistent full-head images from any viewing angle
• create a 3d avatar from a single photo
• train a 3d gan on unstructured in-the-wild face images
• render 3d heads with detailed geometry and hairstyles
• research on 3d-aware generative adversarial networks

When to choose

• you need 360-degree view-consistent 3D head synthesis or single-image 3D avatar reconstruction
• you have NVIDIA GPUs and want a research-grade 3D GAN codebase to build on

When to avoid

• you need a production-ready end-user application rather than research code
• you lack a CUDA-capable NVIDIA GPU
• you need real-time synthesis on consumer hardware without GPU setup

Facets

library · maturity active

machine-learning deep-learning image-processing computer-vision graphics deep-learning computer-vision graphics artificial-intelligence python 3d-gan head-synthesis avatar-generation cvpr-2023 neural-rendering research-code linux gpu cuda

Member repositories

For agents

markdown · JSON · MCP: product_card(name="SizheAn/PanoHead")