# yoyo-nb/Thin-Plate-Spline-Motion-Model

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

Repository: https://github.com/yoyo-nb/Thin-Plate-Spline-Motion-Model
Canonical: https://ross.abutalabs.com/products/thin-plate-spline-motion-model
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: deep-learning, deepfake, face-animation, face-reenactment, image-animation, motion-transfer, pose-transfer, talking-head
Last push: 2024-02-10T23:29:11+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1743, "days_push": 935, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3604, forks 555 (observed 2026-08-28T04:08:11.495564+00:00)

## What it is
The official PyTorch implementation of the CVPR 2022 paper 'Thin-Plate Spline Motion Model for Image Animation'. It animates a source image using motion from a driving video, supporting face reenactment, talking-head generation, and pose transfer with pre-trained models.

## Use cases
- animate a photo using motion from a driving video
- generate talking-head videos from a single face image
- perform face reenactment
- transfer pose from one video to a source image
- train an image animation model on a custom dataset

## When to choose
- you need state-of-the-art thin-plate spline based image animation
- you want pre-trained models for face animation or motion transfer
- you want a research baseline for image animation papers

## When to avoid
- you need a production-ready, actively maintained tool
- you want a simple no-code solution without GPU setup
- your task is unrelated to image/video animation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, video-processing
- domain: computer-vision, deep-learning, image-processing
- platform: python
- tags: face-reenactment, motion-transfer, talking-head, image-animation, deepfake, cvpr-2022, pose-transfer, video, gpu, linux

## Member repositories
- yoyo-nb/Thin-Plate-Spline-Motion-Model (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:11.495564+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:33:43.593602+00:00, confidence not recorded.
  - readme: https://github.com/yoyo-nb/Thin-Plate-Spline-Motion-Model (fetched 2026-08-28T04:08:11.495564+00:00, sha d6d82ac102c2)
- Data as of 2026-08-30T08:39:29.467469+00:00.