snap-research/articulated-animation

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1277 stars · 349 forks observed · 2026-08-28

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

Official research code for the CVPR 2021 paper 'Motion Representations for Articulated Animation' by Snap Research. It animates a static source image using motion extracted from a driving video by identifying and tracking articulated object parts in an unsupervised manner.

Use cases

• animate a photo using motion from a driving video
• face reenactment from a video
• transfer pose from video to a still image
• train an image animation model on my own dataset
• compare against first-order motion model baselines
• generate talking head videos from a single image

When to choose

• you need state-of-the-art articulated image animation with region-based motion representations
• you want pre-trained checkpoints and a quick Colab demo
• you are reproducing or building on CVPR 2021 animation research

When to avoid

• you need a production-ready, supported product with a stable API
• you want real-time animation on CPU or mobile devices
• you need a maintained library with active feature development

Facets

library · maturity maintenance

deep-learning image-processing video-processing machine-learning computer-vision deep-learning machine-learning image-processing python cross-platform image-animation motion-representation first-order-motion-model face-reenactment pose-transfer cvpr-2021 research-code pytorch video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="snap-research/articulated-animation")