DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy

• URL: http://arxiv.org/abs/2512.01302v2
• Date: Mon, 08 Dec 2025 05:26:07 GMT
• Title: DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy
• Authors: Jaewoo Song, Jooyoung Choi, Kanghyun Baek, Sangyub Lee, Daemin Park, Sungroh Yoon,
• Abstract summary: DCText is a training-free visual text generation method that adopts a divide-and-conquer strategy.<n>Our method first decomposes a prompt by extracting and dividing the target text, then assigns each to a designated region.<n>Experiments on single- and multisentence benchmarks show that DCText achieves the best text accuracy without compromising image quality.
• Score: 41.781258763025896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite recent text-to-image models achieving highfidelity text rendering, they still struggle with long or multiple texts due to diluted global attention. We propose DCText, a training-free visual text generation method that adopts a divide-and-conquer strategy, leveraging the reliable short-text generation of Multi-Modal Diffusion Transformers. Our method first decomposes a prompt by extracting and dividing the target text, then assigns each to a designated region. To accurately render each segment within their regions while preserving overall image coherence, we introduce two attention masks - Text-Focus and Context-Expansion - applied sequentially during denoising. Additionally, Localized Noise Initialization further improves text accuracy and region alignment without increasing computational cost. Extensive experiments on single- and multisentence benchmarks show that DCText achieves the best text accuracy without compromising image quality while also delivering the lowest generation latency.

Related papers

• TextGuider: Training-Free Guidance for Text Rendering via Attention Alignment [68.91073792449201]
  We propose TextGuider, a training-free method that encourages accurate and complete text appearance.<n>Specifically, we analyze attention patterns in Multi-Modal Diffusion Transformer(MM-DiT) models, particularly for text-related tokens intended to be rendered in the image.<n>Our method achieves state-of-the-art performance in test-time text rendering, with significant gains in recall and strong results in OCR accuracy and CLIP score.
  arXiv  Detail & Related papers  (2025-12-10T06:18:30Z)
• UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis [38.658170067715965]
  We propose a segmentation-guided framework that uses pixel-level visual text masks as unified conditional inputs.<n>Our approach achieves state-of-the-art performance on the AnyText benchmark.<n>We also introduce two new benchmarks: GlyphMM-benchmark for testing layout and glyph consistency in complex, and MiniText-benchmark for assessing generation quality in small-scale text regions.
  arXiv  Detail & Related papers  (2025-07-01T17:42:19Z)
• GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing [23.64662356622401]
  We present GlyphMastero, a specialized glyph encoder designed to guide the latent diffusion model for generating texts with stroke-level precision.<n>Our method achieves an 18.02% improvement in sentence accuracy over the state-of-the-art scene text editing baseline.
  arXiv  Detail & Related papers  (2025-05-08T03:11:58Z)
• SceneVTG++: Controllable Multilingual Visual Text Generation in the Wild [55.619708995575785]
  The text in natural scene images needs to meet the following four key criteria.<n>The generated text can facilitate to the training of natural scene OCR (Optical Character Recognition) tasks.<n>The generated images have superior utility in OCR tasks like text detection and text recognition.
  arXiv  Detail & Related papers  (2025-01-06T12:09:08Z)
• TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation [21.171612603385405]
  We present TextCenGen, a training-free dynamic background adaptation in the blank region for text-friendly image generation.<n>Our method analyzes cross-attention maps to identify conflicting objects overlapping with text regions and uses a force-directed graph approach to guide their relocation.<n>Our method is plug-and-play, requiring no additional training while well balancing both semantic fidelity and visual quality.
  arXiv  Detail & Related papers  (2024-04-18T01:10:24Z)
• Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Models [63.99110667987318]
  We present DiffText, a pipeline that seamlessly blends foreground text with the background's intrinsic features. With fewer text instances, our produced text images consistently surpass other synthetic data in aiding text detectors.
  arXiv  Detail & Related papers  (2023-11-28T06:51:28Z)
• Self-supervised Scene Text Segmentation with Object-centric Layered Representations Augmented by Text Regions [22.090074821554754]
  We propose a self-supervised scene text segmentation algorithm with layered decoupling of representations derived from the object-centric manner to segment images into texts and background. On several public scene text datasets, our method outperforms the state-of-the-art unsupervised segmentation algorithms.
  arXiv  Detail & Related papers  (2023-08-25T05:00:05Z)
• SpaText: Spatio-Textual Representation for Controllable Image Generation [61.89548017729586]
  SpaText is a new method for text-to-image generation using open-vocabulary scene control. In addition to a global text prompt that describes the entire scene, the user provides a segmentation map. We show its effectiveness on two state-of-the-art diffusion models: pixel-based and latent-conditional-based.
  arXiv  Detail & Related papers  (2022-11-25T18:59:10Z)
• Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors [58.71128866226768]
  Recent text-to-image generation methods have incrementally improved the generated image fidelity and text relevancy. We propose a novel text-to-image method that addresses these gaps by (i) enabling a simple control mechanism complementary to text in the form of a scene. Our model achieves state-of-the-art FID and human evaluation results, unlocking the ability to generate high fidelity images in a resolution of 512x512 pixels.
  arXiv  Detail & Related papers  (2022-03-24T15:44:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.