OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation

• URL: http://arxiv.org/abs/2510.24093v1
• Date: Tue, 28 Oct 2025 06:06:52 GMT
• Title: OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation
• Authors: Agus Gunawan, Samuel Teodoro, Yun Chen, Soo Ye Kim, Jihyong Oh, Munchurl Kim,
• Abstract summary: We propose OmniText, a training-free generalist capable of performing a wide range of Text Image Manipulation tasks.<n>Specifically, we investigate two key properties of cross- and self-attention mechanisms to enable text removal.<n>We present OmniText-Bench, a benchmark dataset for evaluating diverse TIM tasks.
• Score: 34.080740212072655
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent advancements in diffusion-based text synthesis have demonstrated significant performance in inserting and editing text within images via inpainting. However, despite the potential of text inpainting methods, three key limitations hinder their applicability to broader Text Image Manipulation (TIM) tasks: (i) the inability to remove text, (ii) the lack of control over the style of rendered text, and (iii) a tendency to generate duplicated letters. To address these challenges, we propose OmniText, a training-free generalist capable of performing a wide range of TIM tasks. Specifically, we investigate two key properties of cross- and self-attention mechanisms to enable text removal and to provide control over both text styles and content. Our findings reveal that text removal can be achieved by applying self-attention inversion, which mitigates the model's tendency to focus on surrounding text, thus reducing text hallucinations. Additionally, we redistribute cross-attention, as increasing the probability of certain text tokens reduces text hallucination. For controllable inpainting, we introduce novel loss functions in a latent optimization framework: a cross-attention content loss to improve text rendering accuracy and a self-attention style loss to facilitate style customization. Furthermore, we present OmniText-Bench, a benchmark dataset for evaluating diverse TIM tasks. It includes input images, target text with masks, and style references, covering diverse applications such as text removal, rescaling, repositioning, and insertion and editing with various styles. Our OmniText framework is the first generalist method capable of performing diverse TIM tasks. It achieves state-of-the-art performance across multiple tasks and metrics compared to other text inpainting methods and is comparable with specialist methods.

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)
• 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)
• Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search [64.15205542003056]
  We introduce Attention-Guided Alignment (AGA) framework featuring two innovative components: Attention-Guided Mask (AGM) Modeling and Text Enrichment Module (TEM)<n>AGA achieves new state-of-the-art results with Rank-1 accuracy reaching 78.36%, 67.31%, and 67.4% on CUHK-PEDES, ICFG-PEDES, and RSTP, respectively.
  arXiv  Detail & Related papers  (2024-12-19T17:51:49Z)
• TextMaster: A Unified Framework for Realistic Text Editing via Glyph-Style Dual-Control [5.645654441900668]
  We propose TextMaster, a solution capable of accurately editing text across various scenarios and image regions.<n>Our method enhances the accuracy and fidelity of text rendering by incorporating high-resolution standard glyph information.<n>We also propose a novel style injection technique that enables controllable style transfer for the injected text.
  arXiv  Detail & Related papers  (2024-10-13T15:39:39Z)
• CLII: Visual-Text Inpainting via Cross-Modal Predictive Interaction [23.683636588751753]
  State-of-the-art inpainting methods are mainly designed for nature images and cannot correctly recover text within scene text images. We identify the visual-text inpainting task to achieve high-quality scene text image restoration and text completion.
  arXiv  Detail & Related papers  (2024-07-23T06:12:19Z)
• Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval [12.057465578064345]
  The goal of Text-to-Image Person Retrieval (TIPR) is to retrieve specific person images according to the given textual descriptions.<n>We propose a novel TIPR framework to build fine-grained interactions and alignment between person images and the corresponding texts.
  arXiv  Detail & Related papers  (2023-07-18T08:23:46Z)
• TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision [61.186488081379]
  We propose TextFormer, a query-based end-to-end text spotter with Transformer architecture. TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multi-task modeling. It allows for mutual training and optimization of classification, segmentation, and recognition branches, resulting in deeper feature sharing.
  arXiv  Detail & Related papers  (2023-06-06T03:37:41Z)
• Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition [63.6608759501803]
  We propose to recognize artistic text at three levels. corner points are applied to guide the extraction of local features inside characters, considering the robustness of corner structures to appearance and shape. Secondly, we design a character contrastive loss to model the character-level feature, improving the feature representation for character classification. Thirdly, we utilize Transformer to learn the global feature on image-level and model the global relationship of the corner points.
  arXiv  Detail & Related papers  (2022-07-31T14:11:05Z)
• Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting [69.77701325270047]
  This paper presents a weakly supervised pre-training method that can acquire effective scene text representations. Our network consists of an image encoder and a character-aware text encoder that extract visual and textual features. Experiments show that our pre-trained model improves F-score by +2.5% and +4.8% while transferring its weights to other text detection and spotting networks.
  arXiv  Detail & Related papers  (2022-03-08T08:10:45Z)
• Stroke-Based Scene Text Erasing Using Synthetic Data [0.0]
  Scene text erasing can replace text regions with reasonable content in natural images. The lack of a large-scale real-world scene-text removal dataset allows the existing methods to not work in full strength. We enhance and make full use of the synthetic text and consequently train our model only on the dataset generated by the improved synthetic text engine. This model can partially erase text instances in a scene image with a bounding box provided or work with an existing scene text detector for automatic scene text erasing.
  arXiv  Detail & Related papers  (2021-04-23T09:29:41Z)
• AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting [98.08853679310603]
  This work proposes a novel text spotter, named Ambiguity Eliminating Text Spotter (AE TextSpotter) AE TextSpotter learns both visual and linguistic features to significantly reduce ambiguity in text detection. To our knowledge, it is the first time to improve text detection by using a language model.
  arXiv  Detail & Related papers  (2020-08-03T08:40:01Z)

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.