# Edit2Interp: Adapting Image Foundation Models from Spatial Editing to Video Frame Interpolation with Few-Shot Learning

arXiv: https://arxiv.org/abs/2603.15003 · HTML: https://mlsanity.com/paper/2603.15003/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 26 of 26)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Asymmetric Bilateral Motion Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2108.06815/) (2021)
- [Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation](https://mlsanity.com/paper/2303.00440/) (2023)
- [LDMVFI: Video Frame Interpolation with Latent Diffusion Models](https://mlsanity.com/paper/2303.09508/) (2023)
- [Video Interpolation with Diffusion Models](https://mlsanity.com/paper/2404.01203/) (2024)
- [FloLPIPS: A Bespoke Video Quality Metric for Frame Interpoation](https://mlsanity.com/paper/2207.08119/) (2022)
- [Sparse Global Matching for Video Frame Interpolation with Large Motion](https://mlsanity.com/paper/2404.06913/) (2024)
- [ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler](https://mlsanity.com/paper/2410.05651/) (2024)
- [EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation](https://mlsanity.com/paper/2503.15831/) (2025)
- [Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation](https://mlsanity.com/paper/2203.10291/) (2022)
- [Enhanced Bi-directional Motion Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2206.08572/) (2022)
- [Sparse High Rank Adapters](https://mlsanity.com/paper/2406.13175/) (2024)
- [Generalizable Implicit Motion Modeling for Video Frame Interpolation](https://mlsanity.com/paper/2407.08680/) (2024)
- [TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation](https://mlsanity.com/paper/2207.09048/) (2022)
- [OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation](https://mlsanity.com/paper/2403.18092/) (2024)
- [Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN](https://mlsanity.com/paper/2202.07731/) (2022)
- [Hierarchical Flow Diffusion for Efficient Frame Interpolation](https://mlsanity.com/paper/2504.00380/) (2025)
- [Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision](https://mlsanity.com/paper/2505.12532/) (2025)
- [Edit2Restore:Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models](https://mlsanity.com/paper/2601.03391/) (2026)
- [Spatio-Temporal Perception-Distortion Trade-off in Learned Video SR](https://mlsanity.com/paper/2307.01556/) (2023)

## Built on by (most cited first, 1 of 1)

- [Leveraging Image Editing Foundation Models for Data-Efficient CT Metal Artifact Reduction](https://mlsanity.com/paper/2604.05934/) (2026)

## Abstract (arXiv)

Pre-trained image editing models exhibit strong spatial reasoning and object-aware transformation capabilities acquired from billions of image-text pairs, yet they possess no explicit temporal modeling. This paper demonstrates that these spatial priors can be repurposed to unlock temporal synthesis capabilities through minimal adaptation - without introducing any video-specific architecture or motion estimation modules. We show that a large image editing model (Qwen-Image-Edit), originally designed solely for static instruction-based edits, can be adapted for Video Frame Interpolation (VFI) using only 64-256 training samples via Low-Rank Adaptation (LoRA). Our core contribution is revealing that the model's inherent understanding of "how objects transform" in static scenes contains latent temporal reasoning that can be activated through few-shot fine-tuning. While the baseline model completely fails at producing coherent intermediate frames, our parameter-efficient adaptation successfully unlocks its interpolation capability. Rather than competing with task-specific VFI methods trained from scratch on massive datasets, our work establishes that foundation image editing models possess untapped potential for temporal tasks, offering a data-efficient pathway for video synthesis in resource-constrained scenarios. This bridges the gap between image manipulation and video understanding, suggesting that spatial and temporal reasoning may be more intertwined in foundation models than previously recognized