CVOct 15, 2025

Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation

arXiv:2510.13084v11 citationsh-index: 39
Originality Incremental advance
AI Analysis

This addresses efficiency and quality issues in video editing for AI practitioners, representing an incremental improvement over existing diffusion-based methods.

The paper tackles the problem of high computational overhead and memory consumption in text-to-video editing, proposing Edit-Your-Interest, which reduces computational costs and improves visual fidelity, achieving superior efficiency and performance compared to state-of-the-art methods.

Text-to-image (T2I) diffusion models have recently demonstrated significant progress in video editing. However, existing video editing methods are severely limited by their high computational overhead and memory consumption. Furthermore, these approaches often sacrifice visual fidelity, leading to undesirable temporal inconsistencies and artifacts such as blurring and pronounced mosaic-like patterns. We propose Edit-Your-Interest, a lightweight, text-driven, zero-shot video editing method. Edit-Your-Interest introduces a spatio-temporal feature memory to cache features from previous frames, significantly reducing computational overhead compared to full-sequence spatio-temporal modeling approaches. Specifically, we first introduce a Spatio-Temporal Feature Memory bank (SFM), which is designed to efficiently cache and retain the crucial image tokens processed by spatial attention. Second, we propose the Feature Most-Similar Propagation (FMP) method. FMP propagates the most relevant tokens from previous frames to subsequent ones, preserving temporal consistency. Finally, we introduce an SFM update algorithm that continuously refreshes the cached features, ensuring their long-term relevance and effectiveness throughout the video sequence. Furthermore, we leverage cross-attention maps to automatically extract masks for the instances of interest. These masks are seamlessly integrated into the diffusion denoising process, enabling fine-grained control over target objects and allowing Edit-Your-Interest to perform highly accurate edits while robustly preserving the background integrity. Extensive experiments decisively demonstrate that the proposed Edit-Your-Interest outperforms state-of-the-art methods in both efficiency and visual fidelity, validating its superior effectiveness and practicality.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes