Training-Free Occluded Text Rendering via Glyph Priors and Attention-Guided Semantic Blending

• URL: http://arxiv.org/abs/2605.16810v1
• Date: Sat, 16 May 2026 04:58:07 GMT
• Title: Training-Free Occluded Text Rendering via Glyph Priors and Attention-Guided Semantic Blending
• Abstract summary: We present a training-free framework for occluded text rendering with a pretrained FLUX.1-dev backbone.<n>The task requires a model to render recognizable typography and place an occluding object over the intended text region.<n>We propose a restarted dual-stream inference framework that decouples text- preservation from occluder insertion.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a training-free framework for occluded text rendering with a pretrained FLUX.1-dev backbone. The task requires a model to render recognizable typography and place an occluding object over the intended text region. This setting remains difficult for existing text-to-image generators: the occluder often drifts away from the text, while the text may be distorted or appear to float on top of the occluding object. To address this problem, we propose a restarted dual-stream inference framework that decouples text-layout preservation from occluder insertion. A Base Stream provides a clean typographic reference and same-step key/value (K/V) features, while the Edit Stream is conditioned on the occlusion prompt. We further adopt the spectral glyph-prior idea from FreeText and adapt it to stabilize the target text structure during early-to-mid denoising. In the reasoning pass, our method localizes the target text, estimates a text-band region from token-conditioned attention and glyph support, and derives an anchor-aware hard fusion mask for the occluder. In the final edit pass, generation restarts from the same initial noise and applies hard mask-guided image-token K/V replacement at selected attention sites, preserving the Base layout outside the mask while injecting the occluder appearance from the Edit Stream inside the mask. Experiments on representative occluded text scenarios demonstrate substantially improved text readability and competitive occlusion alignment, yielding more stable object-on-text compositions without any model fine-tuning.

Related papers

• GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors [44.606371845449424]
  We introduce GlyphAnchor, a novel text-rendering enhancement method for both text-to-image and image-editing diffusion transformer models.<n> Experiments across multiple backbones and benchmarks, including long, complex, and densely arranged text and rare character scenarios, show that GlyphAnchor consistently improves text fidelity while preserving overall image quality.
  arXiv  Detail & Related papers  (2026-09-02T09:23:23Z)
• TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters [14.200794184177829]
  Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition.<n>We introduce textbfTextRefine, a task-aligned post-training framework that combines supervised fine-tuning with operation-specific reward optimization to address these complementary failure modes.<n>For text insertion, our text-span-level reward jointly assesses semantic fidelity and target-span coverage, penalizes spatial conflicts with products and existing text, and employs a gated structural constraint to preserve non-text regions.<n>For text replacement, our glyph-level reward leverages the connectionist temporal classification (
  arXiv  Detail & Related papers  (2026-08-20T05:07:51Z)
• FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection [28.229261085054745]
  Large-scale text-to-image (T2I) diffusion models excel at opendomain synthesis but still struggle with precise text rendering.<n>We propose textbfFreeText, a training-free, plug-and-play framework that improves text rendering by exploiting intrinsic mechanisms of emphDiffusion Transformer (DiT) models.
  arXiv  Detail & Related papers  (2026-01-02T02:36:48Z)
• 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)
• DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy [41.781258763025896]
  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.
  arXiv  Detail & Related papers  (2025-12-01T05:52:55Z)
• RepText: Rendering Visual Text via Replicating [15.476598851383919]
  We present RepText, which aims to empower pre-trained monolingual text-to-image generation models with the ability to accurately render visual text in user-specified fonts.<n>Specifically, we adopt the setting from ControlNet and additionally integrate language agnostic glyph and position of rendered text to enable generating harmonized visual text.<n>Our approach outperforms existing open-source methods and achieves comparable results to native multi-language closed-source models.
  arXiv  Detail & Related papers  (2025-04-28T12:19:53Z)
• TextDestroyer: A Training- and Annotation-Free Diffusion Method for Destroying Anomal Text from Images [6.7015658051949]
  TextDestroyer is the first training- and annotation-free method for scene text destruction.<n>Our method scrambles text areas in the latent start code using a Gaussian distribution before reconstruction.<n>The advantages of TextDestroyer include: (1) it eliminates labor-intensive data annotation and resource-intensive training; (2) it achieves more thorough text destruction, preventing recognizable traces; and (3) it demonstrates better generalization capabilities, performing well on both real-world scenes and generated images.
  arXiv  Detail & Related papers  (2024-11-01T04:41:00Z)
• First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blending [5.3798706094384725]
  We propose a new visual text blending paradigm including both creating backgrounds and rendering texts. Specifically, a background generator is developed to produce high-fidelity and text-free natural images. We also explore several downstream applications based on our method, including scene text dataset synthesis for boosting scene text detectors.
  arXiv  Detail & Related papers  (2024-10-14T05:23:43Z)
• Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model [81.96954332787655]
  We introduce Diffree, a Text-to-Image (T2I) model that facilitates text-guided object addition with only text control. In experiments, Diffree adds new objects with a high success rate while maintaining background consistency, spatial, and object relevance and quality.
  arXiv  Detail & Related papers  (2024-07-24T03:58:58Z)
• Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis [63.757624792753205]
  We present Zero-Painter, a framework for layout-conditional text-to-image synthesis. Our method utilizes object masks and individual descriptions, coupled with a global text prompt, to generate images with high fidelity.
  arXiv  Detail & Related papers  (2024-06-06T13:02:00Z)
• Text Augmented Spatial-aware Zero-shot Referring Image Segmentation [60.84423786769453]
  We introduce a Text Augmented Spatial-aware (TAS) zero-shot referring image segmentation framework. TAS incorporates a mask proposal network for instance-level mask extraction, a text-augmented visual-text matching score for mining the image-text correlation, and a spatial for mask post-processing. The proposed method clearly outperforms state-of-the-art zero-shot referring image segmentation methods.
  arXiv  Detail & Related papers  (2023-10-27T10:52:50Z)
• Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis [59.10787643285506]
  Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. One critical limitation of these models is the low fidelity of generated images with respect to the text description. We propose a new text-to-image algorithm that adds explicit control over spatial-temporal cross-attention in diffusion models.
  arXiv  Detail & Related papers  (2023-04-07T23:49:34Z)
• Exploring Stroke-Level Modifications for Scene Text Editing [86.33216648792964]
  Scene text editing (STE) aims to replace text with the desired one while preserving background and styles of the original text. Previous methods of editing the whole image have to learn different translation rules of background and text regions simultaneously. We propose a novel network by MOdifying Scene Text image at strokE Level (MOSTEL)
  arXiv  Detail & Related papers  (2022-12-05T02:10:59Z)

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.