Metraipolis › archive › dc_46cda848079d
Enhanced Video Text Editing with Trajectory-Aligned Glyph Rendering — arXiv:2609.34178
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34178
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:51:55.856Z
- SHA-256 of the archived text
bb70f051fd23812b826758e5b99c1341b15a6a75f6663f895b80d54d75412503- Stable URL of this page
https://metraipolis.com/documento/dc_46cda848079d
How to cite
Enhanced Video Text Editing with Trajectory-Aligned Glyph Rendering — arXiv:2609.34178 — arXiv (en), https://arxiv.org/abs/2609.34178 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46cda848079d (Metraipolis archive dc_46cda848079d, sha256 bb70f051fd23812b826758e5b99c1341b15a6a75f6663f895b80d54d75412503)
BibTeX
@misc{dc46cda848079d,
title = {Enhanced Video Text Editing with Trajectory-Aligned Glyph Rendering — arXiv:2609.34178},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34178},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46cda848079d; sha256 bb70f051fd23812b826758e5b99c1341b15a6a75f6663f895b80d54d75412503},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34178. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video text editing aims to replace or add text in a video while keeping the rest of the video unchanged, which requires the edited text to be correct in every frame and to move coherently with the scene. Despite the remarkable progress of video diffusion models, they struggle to reproduce exact stroke structures and often produce garbled or wrong characters, especially for characters with complex strokes. To address this, we propose a trajectory-aligned glyph rendering reference that provides explicit per-frame glyph guidance following the position and perspective of the text, and a depth-normalized recognizer feature supervision that supervises the generated text on multi-depth features of a frozen text recognizer with per-depth normalized errors, targeting stroke errors overlooked by the diffusion loss. We further build VTEdit, a benchmark of 288 real-scene clips with 440 annotated text trajectories covering text replacement and text addition, which will be publicly released to facilitate future research. Experiments on VTEdit show that our method outperforms image text editing methods, video editing methods, and commercial models in text accuracy and background preservation, achieving a sentence accuracy of 0.9408, and receives the highest preference in a user study. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.34178 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T23:29:27.308Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).