SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation

ArXi:2506.23690v2 Announce Type: replace Diffusion-based video motion customization facilitates the acquisition of human motion representations from a few video samples, while achieving arbitrary subjects transfer through precise textual conditioning. Existing approaches often rely on semantic-level alignment, expecting the model to learn new motion concepts and combine them with other entities (e.g., ''cats'' or ''dogs'') to produce visually appealing results.