arXiv cs.AI· Kai Zeng, Moran Li, Zhengwei Wang, Yingchen Yu, Yiheng Lin, Ruichuan An, Ming Lu, Qi She, Wentao Zhang·· 12 小时前AI 评分31
SteerVTE：用风格与字形控制实现无缝视频文本编辑
SteerVTE: Seamless Video Text Editing with Style and Glyph Control
AI 导读
SteerVTE 通过风格与字形控制驱动冻结的视频扩散模型完成精确视频文本编辑，在文本准确度、风格一致性和时序连贯性上显著优于现有视频编辑基线。该框架在冻结的扩散 Transformer 上挂载轻量文本上下文适配器，包含捕捉原文字视觉属性的风格编码器和在线级、字符级双粒度编码目标文本的字形编码器。
正文 · 原文
Abstract:Visual text editing aims to precisely modify text in images and videos while preserving stylistic consistency and visual realism. Despite significant advances in the image domain, video text editing remains largely unexplored: it is a localized task demanding stroke-level precision within small text regions, which compounds the challenges of cross-frame accuracy, temporal coherence, and stylistic fidelity. We introduce SteerVTE, a unified framework that steers a frozen video diffusion model to perform precise Video Text Editing through style and glyph control. Built on a frozen diffusion transformer, SteerVTE attaches a lightweight text context adapter with two complementary modules: a style encoder capturing the original text's visual attributes, and dual-granularity glyph encoders encoding the target text at both the line and character levels. To overcome the inherently weak text rendering priors of video foundation models, we further propose a glyph-aware spatial-focal loss and a three-stage progressive training curriculum that scales from image to video data. To support large-scale training, we also develop an automatic synthesis pipeline and construct SteerVTE-1M, a dataset of one million triplets spanning diverse scenes, fonts, and stylistic effects. Extensive experiments demonstrate that SteerVTE substantially outperforms existing video editing baselines across text accuracy, style consistency, and temporal coherence. Our project page is available at this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.23254 [cs.CV] |
| (or arXiv:2606.23254v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.23254 arXiv-issued DOI via DataCite |
|
| Journal reference: | NeurIPS 2026 |
Submission history
From: Kai Zeng [view email]
[v1]
Mon, 22 Jun 2026 12:37:15 UTC (45,091 KB)
[v2]
Fri, 23 Oct 2026 08:31:42 UTC (8,783 KB)
来源：arXiv cs.AI · arxiv.org