svip-lab/impersonator

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1717 stars · 308 forks observed · 2026-08-28

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

A PyTorch implementation of Liquid Gating GAN (ICCV 2019) that performs human motion imitation, appearance transfer, and novel view synthesis in a unified framework. It uses 3D body mesh recovery to disentangle pose and shape, plus a Liquid Warping Block to preserve source identity, texture, and style in generated images.

Use cases

• make a person in an image follow a motion from a video
• transfer clothing appearance between people in photos
• generate novel views of a person from a single image
• animate a still photo with a driving pose sequence
• research human motion transfer with GANs
• evaluate motion imitation on the iPER dataset

When to choose

• you need research-grade human motion imitation or appearance transfer in PyTorch
• you want a unified model handling motion, appearance, and view synthesis
• you want to reproduce or build on the ICCV 2019 Liquid Warping GAN paper
• you have a CUDA GPU with at least ~4GB memory

When to avoid

• you need a production-ready, actively maintained product
• you work on Windows or macOS without testing effort
• you need real-time or mobile inference
• you want a simple API without downloading checkpoints and building thirdparty renderers

Facets

library · maturity maintenance

machine-learning deep-learning image-processing computer-vision deep-learning computer-vision image-processing python gan pytorch motion-imitation appearance-transfer novel-view-synthesis human-pose research-code iccv-2019 linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="svip-lab/impersonator")