arXiv：cs.AI· Xinghao Chen, Xiangbo Gao, Jiongze Yu, Yuheng Wu, Zhengzhong Tu·· 5 小时前
ViTeX-Bench：高保真视频场景文本编辑基准发布
ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing
AI 导读
ViTeX-Bench 是一个面向视频场景文本编辑的基准套件，包含 387 段真实 720p 视频，其中 230 段为经审核的配对编辑数据用于训练、157 段为冻结评测集，并通过 13 项指标从文本正确性、视觉与时间质量、编辑局部性三个维度评测。
正文
Abstract:Recent video generation is increasingly realistic and controllable, yet video editing remains less developed, particularly for precise local edits that must preserve the original scene dynamics. Video scene text editing replaces text on scene surfaces, such as storefront signs, whiteboards, and product labels, while preserving the surrounding content, motion, and camera dynamics. Although scene text editing is well studied for images, video scene text editing that achieves high visual quality, temporal consistency, and edit locality remains underexplored. Existing resources offer limited paired real-video data, and general video-editing metrics do not directly measure whether the requested text remains correct over time. We introduce ViTeX-Bench, a benchmark suite comprising ViTeX-Dataset and a three-axis evaluation protocol. The dataset contains 387 real-world 720p videos with text-region masks and editing instructions: 230 provide reviewed, pipeline-generated paired edits for training, and 157 form a frozen evaluation split. The protocol evaluates text correctness, visual and temporal quality, and edit locality through 13 metrics, with one primary metric per axis and a Pareto comparison of their trade-offs. OCR calibration, human evaluation, and annotation-sensitivity analyses support the interpretation of these scores. Across eight baselines from four editing families, accurate text, temporal stability, and scene preservation remain difficult to achieve together. We also release ViTeX-Edit-14B, an open-source reference editor fine-tuned on the paired training split with motion-aligned glyph-video conditioning. It achieves CharAcc 0.688, the highest mean among the evaluated video-native editors, and the lowest comparable text-crop Warp among raw editor outputs. ViTeX-Bench provides a reproducible foundation for studying these trade-offs in video scene text editing.
| Comments: | Accepted to NeurIPS 2026 (Evaluations and Datasets Track). 27 pages (10-page main text), 5 figures, 12 tables. Project page: this https URL v2: correct the ViTeX-Edit-14B results, add ablation study on disabling glyphs |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.40356 [cs.CV] |
| (or arXiv:2609.40356v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2609.40356 arXiv-issued DOI via DataCite |
Submission history
From: Xinghao Chen [view email]
[v1]
Wed, 30 Sep 2026 17:59:33 UTC (6,231 KB)
[v2]
Sun, 11 Oct 2026 18:22:18 UTC (6,139 KB)
来源：arXiv：cs.AI · arxiv.org