ShoulderShot: Generating Over-the-Shoulder Dialogue Videos
This addresses a practical need for filmmakers and advertisers to create varied, emotionally engaging dialogue scenes efficiently, though it appears incremental as it builds on existing video generation techniques.
The paper tackles the problem of generating over-the-shoulder dialogue videos, which are important for films and ads but underexplored in video generation, by proposing ShoulderShot to maintain character consistency and spatial continuity while enabling long dialogues. The results show it surpasses existing methods in shot-reverse-shot layout, spatial continuity, and dialogue length flexibility.
Over-the-shoulder dialogue videos are essential in films, short dramas, and advertisements, providing visual variety and enhancing viewers' emotional connection. Despite their importance, such dialogue scenes remain largely underexplored in video generation research. The main challenges include maintaining character consistency across different shots, creating a sense of spatial continuity, and generating long, multi-turn dialogues within limited computational budgets. Here, we present ShoulderShot, a framework that combines dual-shot generation with looping video, enabling extended dialogues while preserving character consistency. Our results demonstrate capabilities that surpass existing methods in terms of shot-reverse-shot layout, spatial continuity, and flexibility in dialogue length, thereby opening up new possibilities for practical dialogue video generation. Videos and comparisons are available at https://shouldershot.github.io.