{"ID":2862254,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01186","arxiv_id":"2510.01186","title":"ASTRA: Let Arbitrary Subjects Transform in Video Editing","abstract":"While existing video editing methods excel with single subjects, they struggle in dense, multi-subject scenes, frequently suffering from attention dilution and mask boundary entanglement that cause attribute leakage and temporal instability. To address this, we propose ASTRA, a training-free framework for seamless, arbitrary-subject video editing. Without requiring model fine-tuning, ASTRA precisely manipulates multiple designated subjects while strictly preserving non-target regions. It achieves this via two core components: a prompt-guided multimodal alignment module that generates robust conditions to mitigate attention dilution, and a prior-based mask retargeting module that produces temporally coherent mask sequences to resolve boundary entanglement. Functioning as a versatile plug-and-play module, ASTRA seamlessly integrates with diverse mask-driven video generators. Extensive experiments on our newly constructed benchmark, MSVBench, demonstrate that ASTRA consistently outperforms state-of-the-art methods. Code, models, and data are available at https://github.com/XWH-A/ASTRA.","short_abstract":"While existing video editing methods excel with single subjects, they struggle in dense, multi-subject scenes, frequently suffering from attention dilution and mask boundary entanglement that cause attribute leakage and temporal instability. To address this, we propose ASTRA, a training-free framework for seamless, arb...","url_abs":"https://arxiv.org/abs/2510.01186","url_pdf":"https://arxiv.org/pdf/2510.01186v2","authors":"[\"Fei Shen\",\"Weihao Xu\",\"Rui Yan\",\"Dong Zhang\",\"Xiangbo Shu\",\"Jinhui Tang\",\"Maocheng Zhao\"]","published":"2025-10-01T17:59:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":608885,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2862254,"paper_url":"https://arxiv.org/abs/2510.01186","paper_title":"ASTRA: Let Arbitrary Subjects Transform in Video Editing","repo_url":"https://github.com/XWH-A/ASTRA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}