Modern video generators can synthesize convincing scenes while rendering a few characters incorrectly, omitting requested text, or changing it across frames. Measuring these failures is harder than applying OCR independently to each frame: when a scene contains multiple text targets and multiple noisy OCR regions, the evaluator must first determine which observation belongs to which intended text. We introduce TextVBench, a benchmark and evaluation framework that formulates visual-text evaluation as a multi-target, multi-instance spatiotemporal correspondence problem. TextVBench contains two complementary tracks: TextVBench-T2V measures the creation and maintenance of prompt-specified text, while TextVBench-Ref2V measures preservation of text from reference images. Both tracks use target-conditioned candidate selection rather than unconstrained VLM transcription, support one target mapping to multiple OCR regions, and separate frame-level spatial fidelity from cross-frame temporal fidelity. A length-weighted harmonic score summarizes these factors, while extra-text diagnostics expose failure modes hidden by a single OCR score. The benchmark is organized around controlled text, layout, carrier, and motion attributes so that aggregate scores can be traced back to specific capability limits. Across the evaluated model runs, MiniMax-H3 reaches a T2V TextVScore of 68.32, while the strongest Ref2V score is 56.51; attribute slices reveal a pronounced drop as the number of simultaneous reference text regions increases.
Rendering-Refined Stable Diffusion for Privacy Compliant Synthetic Data
University of California, Davis（加利福尼亚大学戴维斯分校）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Australian National University（澳大利亚国立大学）；Sony AI, Sony Research（索尼人工智能，索尼研究院）
TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；College of Computer Science, Nankai University（南开大学计算机学院）
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
School of Software, Beihang University, Beijing, China（北京航空航天大学软件学院）；Department of Computer Science, The University of Hong Kong, Hong Kong, China（香港大学计算机科学系）；College of Computer Science and Technology, Zhejiang University, Hangzhou, China（浙江大学计算机科学与技术学院）
University of Surrey（萨里大学）；The University of Hong Kong（香港大学）；Imperial College London（帝国理工学院）；iFlyTek-Surrey Joint Research Centre on AI（科大讯飞-萨里人工智能联合研究中心）；Surrey Institute for People-Centred AI（萨里以人为本人工智能研究所）
Large text-to-image models achieved a remarkable leap in the evolution of AI, enabling high-quality and diverse synthesis of images from a given text prompt. However, these models lack the ability to mimic the appearance of subjects in a given reference set and synthesize novel renditions of them in different contexts. In this work, we present a new approach for "personalization" of text-to-image diffusion models. Given as input just a few images of a subject, we fine-tune a pretrained text-to-image model such that it learns to bind a unique identifier with that specific subject. Once the subj…
