arXiv cs.AI· Xinyu Chen, Song Wu, Dingbao Shao, Jiahang Li, Jiang Lin, Yuhang Liu, Duo Li, Jiaxin Hu, Shengrong Gu, Liang Li, Qian Wang, Junlan Feng, Ying Tai, Jian Yang, Zili Yi·· 14 小时前AI 评分32
SemantiScene-Edit：面向指令视频编辑的专家合成监督与双路径源条件
SemantiScene-Edit: Expert-Synthesized Supervision and Dual-Path Source Conditioning for Instruction-Based Video Editing
AI 导读
SemantiScene-Edit 将多模态编码器与预训练视频扩散 Transformer 结合，通过可学习查询和跨注意力传递语义上下文，并在 patch embedding 前拼接源视频 latent 与噪声目标 latent 以保留内容。
正文 · 原文
Authors:Xinyu Chen, Song Wu, Dingbao Shao, Jiahang Li, Jiang Lin, Yuhang Liu, Duo Li, Jiaxin Hu, Shengrong Gu, Liang Li, Qian Wang, Junlan Feng, Ying Tai, Jian Yang, Zili Yi
Abstract:Instruction-guided video editing requires executing a requested change while preserving the source video's appearance and temporal structure. We present SemantiScene-Edit, a video editor that couples a multimodal encoder with a pretrained video diffusion transformer. The encoder jointly processes source frames and the editing instruction, and learnable queries convey their semantic context to the generator through a trainable connector and cross-attention. A complementary visual pathway concatenates source-video latents with noisy target latents before patch embedding, supplying dense spatial and temporal information for content preservation. We train the model with flow matching and a three-stage image--video curriculum comprising semantic alignment, joint adaptation, and high-resolution refinement. To support training, we construct over 1.2 million instruction-conditioned video-editing records covering object addition, removal, replacement, and attribute modification. We also construct a 100-case benchmark for evaluating instruction execution, source preservation, temporal consistency, and visual quality. Comparative experiments show that SemantiScene-Edit effectively follows editing instructions while retaining source content. At inference, the model requires only a source video and a natural-language instruction.
| Subjects: | Artificial Intelligence (cs.AI); Graphics (cs.GR) |
| Cite as: | arXiv:2609.26015 [cs.AI] |
| (or arXiv:2609.26015v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.26015 arXiv-issued DOI via DataCite |
Submission history
From: Jiahang Li [view email]
[v1]
Tue, 22 Sep 2026 11:18:56 UTC (670 KB)
[v2]
Thu, 29 Oct 2026 08:02:49 UTC (21,768 KB)
来源：arXiv cs.AI · arxiv.org