about
Integrating Explicit Structural Guidance into Inbetween Frame Generation (arxiv.org)
2 points by PaulHoule on Jul 31, 2025 | hide | past | pdf | discuss on HN

In plain words: A tool that fills in the frames between two key drawings by following an outline of the character's structure, so there's less guesswork about how things should move. It also copies the character's look from both end drawings, keeping the character looking the same throughout.

Abstract · StructInbet: Integrating Explicit Structural Guidance into Inbetween Frame Generation

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.

Zhenglin Pan, Haoran Xie
arXiv:2507.13377 · cs.GR, cs.CV · submitted Jul 15, 2025
abstract · pdf · html · 3 pages, 3 figures. SIGGRAPH 2025 Poster

add comment on HN