StructInbet: Integrating Explicit Structural Guidance into Inbetween Frame Generation
This work addresses the challenge of generating smooth and consistent animations for animators and video editors, though it appears incremental by building on existing inbetweening methods.
The authors tackled the problem of ambiguous pixel trajectories in inbetween frame generation by introducing explicit structural guidance, resulting in a system that generates controllable transitions with improved character appearance consistency.
In this paper, we propose StructInbet, an inbetweening system designed to generate controllable transitions over explicit structural guidance. StructInbet introduces two key contributions. First, we propose explicit structural guidance to the inbetweening problem to reduce the ambiguity inherent in pixel trajectories. Second, we adopt a temporal attention mechanism that incorporates visual identity from both the preceding and succeeding keyframes, ensuring consistency in character appearance.