# SAGE: Structure-Aware Generative Video Transitions between Diverse Clips

arXiv: https://arxiv.org/abs/2510.24667 · HTML: https://mlsanity.com/paper/2510.24667/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [Depth-Aware Video Frame Interpolation](https://mlsanity.com/paper/1904.00830/) (2019)
- [SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction](https://mlsanity.com/paper/2310.20700/) (2023)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [FILM: Frame Interpolation for Large Motion](https://mlsanity.com/paper/2202.04901/) (2022)
- [Video Interpolation with Diffusion Models](https://mlsanity.com/paper/2404.01203/) (2024)
- [DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing](https://mlsanity.com/paper/2312.07409/) (2023)
- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features](https://mlsanity.com/paper/2311.17024/) (2023)
- [Generative Inbetweening through Frame-wise Conditions-Driven Video Generation](https://mlsanity.com/paper/2412.11755/) (2024)
- [EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation](https://mlsanity.com/paper/2503.15831/) (2025)
- [TVG: A Training-free Transition Video Generation Method with Diffusion Models](https://mlsanity.com/paper/2408.13413/) (2024)
- [AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation](https://mlsanity.com/paper/2506.01061/) (2025)
- [Versatile Transition Generation with Image-to-Video Diffusion](https://mlsanity.com/paper/2508.01698/) (2025)
- [MatchDiffusion: Training-free Generation of Match-cuts](https://mlsanity.com/paper/2411.18677/) (2024)

## Built on by (most cited first, 2 of 2)

- [LAMP: Language-Assisted Motion Planning for Controllable Video Generation](https://mlsanity.com/paper/2512.03619/) (2025)
- [Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos](https://mlsanity.com/paper/2604.17749/) (2026)

## Abstract (arXiv)

Video transitions aim to synthesize intermediate frames between two clips, but naive approaches such as linear blending introduce artifacts that limit professional use or break temporal coherence. Traditional techniques (cross-fades, morphing, frame interpolation) and recent generative inbetweening methods can produce high-quality plausible intermediates, but they struggle with bridging diverse clips involving large temporal gaps or significant semantic differences, leaving a gap for content-aware and visually coherent transitions. We address this challenge by drawing on artistic workflows, distilling strategies such as aligning silhouettes and interpolating salient features to preserve structure and perceptual continuity. Building on these strategies, we propose SAGE (Structure-Aware Generative vidEo transitions) as a simple yet effective zeroshot approach that combines structural guidance, provided via line maps and motion flow, with generative synthesis, enabling smooth, motion-consistent transitions without fine-tuning. Extensive experiments and comparison with current alternatives, namely [FILM, TVG, DiffMorpher, VACE, GI], demonstrate that SAGE outperforms both classical and the latest generative baselines on quantitative metrics and user studies for producing transitions between diverse clips. The simple method effectively bypasses the need to acquire suitable training data, which is particularly difficult in our creative setting involving diverse clips. Code is available via the project page at https://kan32501.github.io/sage.github.io/.