GACA-DiT: Diffusion-based Dance-to-Music Generation with Genre-Adaptive Rhythm and Context-Aware Alignment

Researchers propose GACA-DiT, a new AI framework that generates music synchronized with dance movements using diffusion transformers. The system addresses limitations of existing methods by incorporating genre-adaptive rhythm extraction and context-aware temporal alignment for better synchronization between dance and music.

• →GACA-DiT uses diffusion transformers to generate music that aligns rhythmically and temporally with dance movements.
• →The framework introduces genre-adaptive rhythm extraction that captures fine-grained, genre-specific rhythm patterns.
• →A context-aware temporal alignment module resolves timing mismatches between dance and music features.
• →Testing on AIST++ and TikTok datasets shows superior performance compared to existing methods.
• →The research addresses weaknesses in current dance-to-music generation systems that rely on coarse rhythm embeddings.