# Image Animation with Perturbed Masks

arXiv: https://arxiv.org/abs/2011.06922 · HTML: https://mlsanity.com/paper/2011.06922/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [LivePhoto: Real Image Animation with Text-guided Motion Control](https://mlsanity.com/paper/2312.02928/) (2023)
- [MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation](https://mlsanity.com/paper/2412.05848/) (2024)
- [Differential Motion Evolution for Fine-Grained Motion Deformation in Unsupervised Image Animation](https://mlsanity.com/paper/2110.04658/) (2021)
- [MaskRenderer: 3D-Infused Multi-Mask Realistic Face Reenactment](https://mlsanity.com/paper/2309.05095/) (2023)
- [ImPoster: Text and Frequency Guidance for Subject Driven Action Personalization using Diffusion Models](https://mlsanity.com/paper/2409.15650/) (2024)
- [One-shot Human Motion Transfer via Occlusion-Robust Flow Prediction and Neural Texturing](https://mlsanity.com/paper/2412.06174/) (2024)
- [Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models](https://mlsanity.com/paper/2601.07287/) (2026)
- [Image Animation with Keypoint Mask](https://mlsanity.com/paper/2112.10457/) (2021)

## Abstract (arXiv)

We present a novel approach for image-animation of a source image by a driving video, both depicting the same type of object. We do not assume the existence of pose models and our method is able to animate arbitrary objects without the knowledge of the object's structure. Furthermore, both, the driving video and the source image are only seen during test-time. Our method is based on a shared mask generator, which separates the foreground object from its background, and captures the object's general pose and shape. To control the source of the identity of the output frame, we employ perturbations to interrupt the unwanted identity information on the driver's mask. A mask-refinement module then replaces the identity of the driver with the identity of the source. Conditioned on the source image, the transformed mask is then decoded by a multi-scale generator that renders a realistic image, in which the content of the source frame is animated by the pose in the driving video. Due to the lack of fully supervised data, we train on the task of reconstructing frames from the same video the source image is taken from. Our method is shown to greatly outperform the state-of-the-art methods on multiple benchmarks. Our code and samples are available at https://github.com/itsyoavshalev/Image-Animation-with-Perturbed-Masks.