arXiv：cs.AI· Mehrajul Abadin Miraj, Md. Mahmudul Hasan, Meherun Farzana, Aniket Joarder, Mahmudul Hasan, Abir Chakraborty Partha, Md. Ahasanul Alam, Redwan Ahmed Rizvee, Md. Fahim Arefin, Md Mahmudur Rahman, Md. Tanvir Alam, Md Mosaddek Khan·· 9 小时前
ELECT：在渲染前确定身份，实现可扩展的故事可视化
ELECT: Settling Identity Before Rendering for Scalable Story Visualization
AI 导读
ELECT 提出一种免训练的故事可视化方法，通过语言引导的场景-实体映射和从模型自身草稿中选举出的固定锚点，在最终渲染前确定跨帧身份，使渲染阶段单帧成本不随故事长度增长。
正文
Authors:Mehrajul Abadin Miraj, Md. Mahmudul Hasan, Meherun Farzana, Aniket Joarder, Mahmudul Hasan, Abir Chakraborty Partha, Md. Ahasanul Alam, Redwan Ahmed Rizvee, Md. Fahim Arefin, Md Mahmudur Rahman, Md. Tanvir Alam, Md Mosaddek Khan
Abstract:Training-free story visualization without reference images must preserve recurring entities across frames while scaling to long narratives. Existing methods typically maintain consistency by conditioning each frame on other frames of the same story, coupling generation time, VRAM, or both to story length. We introduce ELECT, which instead settles cross-frame identity before final rendering through a language-guided scene-entity mapping and stationary anchors elected from the model's own drafts. This makes the per-frame cost of the final rendering pass independent of story length. Joint attention exceeds 96 GB of VRAM at 32 scenes, whereas ELECT remains at 8.3 s per frame and under 20 GB VRAM from 10 to 1000 scenes. On the Story50 long-story benchmark, ELECT reaches 0.833 average Character Consistency Similarity (aCCS), compared with 0.826 for ten-round refinement, at one seventh of its generation cost, with lower text alignment (0.327 vs. 0.340). At 1000 scenes, to our knowledge, the first evaluation of training-free story visualization at this length, ELECT exceeds ten-round refinement by 0.017 aCCS and the nearest flat-cost baseline by 0.091, while also surpassing refinement in text alignment at one twenty-fourth of its generation time. These results show that long-horizon consistency need not require increasingly expensive inter-frame conditioning as stories grow.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.15555 [cs.CV] |
| (or arXiv:2610.15555v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15555 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mehrajul Miraj Miraj [view email]
[v1]
Sun, 11 Oct 2026 11:57:18 UTC (7,659 KB)
来源：arXiv：cs.AI · arxiv.org