AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917951521685504 |
|---|---|
| author | Yun, Kwan Hong, Seokhyeon Kim, Chaelin Noh, Junyong |
| author_facet | Yun, Kwan Hong, Seokhyeon Kim, Chaelin Noh, Junyong |
| contents | Despite recent advancements in learning-based motion in-betweening, a key limitation has been overlooked: the requirement for character-specific datasets. In this work, we introduce AnyMoLe, a novel method that addresses this limitation by leveraging video diffusion models to generate motion in-between frames for arbitrary characters without external data. Our approach employs a two-stage frame generation process to enhance contextual understanding. Furthermore, to bridge the domain gap between real-world and rendered character animations, we introduce ICAdapt, a fine-tuning technique for video diffusion models. Additionally, we propose a ``motion-video mimicking'' optimization technique, enabling seamless motion generation for characters with arbitrary joint structures using 2D and 3D-aware features. AnyMoLe significantly reduces data dependency while generating smooth and realistic transitions, making it applicable to a wide range of motion in-betweening tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08417 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models Yun, Kwan Hong, Seokhyeon Kim, Chaelin Noh, Junyong Graphics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multimedia 68U05 I.3.7; I.4.9 Despite recent advancements in learning-based motion in-betweening, a key limitation has been overlooked: the requirement for character-specific datasets. In this work, we introduce AnyMoLe, a novel method that addresses this limitation by leveraging video diffusion models to generate motion in-between frames for arbitrary characters without external data. Our approach employs a two-stage frame generation process to enhance contextual understanding. Furthermore, to bridge the domain gap between real-world and rendered character animations, we introduce ICAdapt, a fine-tuning technique for video diffusion models. Additionally, we propose a ``motion-video mimicking'' optimization technique, enabling seamless motion generation for characters with arbitrary joint structures using 2D and 3D-aware features. AnyMoLe significantly reduces data dependency while generating smooth and realistic transitions, making it applicable to a wide range of motion in-betweening tasks. |
| title | AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models |
| topic | Graphics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multimedia 68U05 I.3.7; I.4.9 |
| url | https://arxiv.org/abs/2503.08417 |