ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 3129-3137
DOI: 10.1609/aaai.v40i4.37306 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yiyang Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
Training-free video object editing aims to achieve precise object-level manipulation, including object insertion, swapping, and deletion. However, it faces significant challenges in maintaining fidelity and temporal consistency. Existing methods, often designed for U-Net architectures, suffer from two primary limitations: inaccurate inversion due to first-order solvers, and contextual conflicts caused by crude "hard" feature replacement. These issues are more challenging in Diffusion Transformers (DiTs), where the unsuitability of prior layer-selection heuristics makes effective guidance challenging. To address these limitations, we introduce ContextFlow, a novel training-free framework for DiT-based video object editing. In detail, we first employ a high-order Rectified Flow solver to establish a robust editing foundation. The core of our framework is Adaptive Context Enrichment (for specifying what to edit), a mechanism that addresses contextual conflicts. Instead of replacing features, it enriches the self-attention context by concatenating Key-Value pairs from parallel reconstruction and editing paths, empowering the model to dynamically fuse information. Additionally, to determine where to apply this enrichment (for specifying where to edit), we propose a systematic, data-driven analysis to identify task-specific vital layers. Based on a novel Guidance Responsiveness Metric, our method pinpoints the most influential DiT blocks for different tasks (e.g., insertion, swapping), enabling targeted and highly effective guidance. Extensive experiments show that ContextFlow significantly outperforms existing training-free methods and even surpasses several state-of-the-art training-based approaches, delivering temporally coherent, high-fidelity results.
Zitieren
APA
Chen, Y., He, X., Ma, X., & Ma, J. (2026). ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 3129-3137. https://doi.org/10.1609/aaai.v40i4.37306
Vancouver
Chen Y, He X, Ma X, Ma J. ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):3129-3137. doi:10.1609/aaai.v40i4.37306
BibTeX
@article{Chen2026,
author = {Chen, Yiyang and He, Xuanhua and Ma, Xiujun and Ma, Jack},
title = {ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {4},
pages = {3129--3137},
doi = {10.1609/aaai.v40i4.37306}
}
EUVIMED