# AnaMoDiff: 2D Analogical Motion Diffusion via Disentangled Denoising

arXiv: https://arxiv.org/abs/2402.03549 · HTML: https://mlsanity.com/paper/2402.03549/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 22 of 22)

- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [Everybody Dance Now](https://mlsanity.com/paper/1808.07371/) (2018)
- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [Thin-Plate Spline Motion Model for Image Animation](https://mlsanity.com/paper/2203.14367/) (2022)
- [Animating Arbitrary Objects via Deep Motion Transfer](https://mlsanity.com/paper/1812.08861/) (2018)
- [Skeleton-Aware Networks for Deep Motion Retargeting](https://mlsanity.com/paper/2005.05732/) (2020)
- [Recycle-GAN: Unsupervised Video Retargeting](https://mlsanity.com/paper/1808.05174/) (2018)
- [LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation](https://mlsanity.com/paper/2310.10769/) (2023)
- [Flow-Grounded Spatial-Temporal Video Prediction from Still Images](https://mlsanity.com/paper/1807.09755/) (2018)
- [Breathing Life Into Sketches Using Text-to-Video Priors](https://mlsanity.com/paper/2311.13608/) (2023)
- [Learning Character-Agnostic Motion for Motion Retargeting in 2D](https://mlsanity.com/paper/1905.01680/) (2019)
- [LEO: Generative Latent Image Animator for Human Video Synthesis](https://mlsanity.com/paper/2305.03989/) (2023)
- [DragVideo: Interactive Drag-style Video Editing](https://mlsanity.com/paper/2312.02216/) (2023)
- [Structure-Aware Motion Transfer with Deformable Anchor Model](https://mlsanity.com/paper/2204.05018/) (2022)
- [AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints](https://mlsanity.com/paper/2205.10636/) (2022)
- [Example-based Motion Synthesis via Generative Motion Matching](https://mlsanity.com/paper/2306.00378/) (2023)
- [CharacterGAN: Few-Shot Keypoint Character Animation and Reposing](https://mlsanity.com/paper/2102.03141/) (2021)
- [Motion Transformer for Unsupervised Image Animation](https://mlsanity.com/paper/2209.14024/) (2022)
- [JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting](https://mlsanity.com/paper/2106.09679/) (2021)

## Built on by (most cited first, 4 of 4)

- [AniClipart: Clipart Animation with Text-to-Video Priors](https://mlsanity.com/paper/2404.12347/) (2024)
- [Enhancing Sketch Animation: Text-to-Video Diffusion Models with Temporal Consistency and Rigidity Constraints](https://mlsanity.com/paper/2411.19381/) (2024)
- [Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion](https://mlsanity.com/paper/2408.00458/) (2024)
- [Vector sketch animation generation with differentiable motion trajectories](https://mlsanity.com/paper/2509.25857/) (2025)

## Abstract (arXiv)

We present AnaMoDiff, a novel diffusion-based method for 2D motion analogies that is applied to raw, unannotated videos of articulated characters. Our goal is to accurately transfer motions from a 2D driving video onto a source character, with its identity, in terms of appearance and natural movement, well preserved, even when there may be significant discrepancies between the source and driving characters in their part proportions and movement speed and styles. Our diffusion model transfers the input motion via a latent optical flow (LOF) network operating in a noised latent space, which is spatially aware, efficient to process compared to the original RGB videos, and artifact-resistant through the diffusion denoising process even amid dense movements. To accomplish both motion analogy and identity preservation, we train our denoising model in a feature-disentangled manner, operating at two noise levels. While identity-revealing features of the source are learned via conventional noise injection, motion features are learned from LOF-warped videos by only injecting noise with large values, with the stipulation that motion properties involving pose and limbs are encoded by higher-level features. Experiments demonstrate that our method achieves the best trade-off between motion analogy and identity preservation.