CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization

• URL: http://arxiv.org/abs/2603.07543v1
• Date: Sun, 08 Mar 2026 09:06:13 GMT
• Title: CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization
• Abstract summary: We introduce Patch Contrastive Enhancement and Style-Aware Quantization via Denoising Diffusion (CONSTANT)<n>CONSTANT is a novel one-shot handwriting generation via diffusion model.<n>It produces highly detailed images of its method over state-of-the-art approaches.
• Score: 0.2446672595462589
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: One-shot styled handwriting image generation, despite achieving impressive results in recent years, remains challenging due to the difficulty in capturing the intricate and diverse characteristics of human handwriting by using solely a single reference image. Existing methods still struggle to generate visually appealing and realistic handwritten images and adapt to complex, unseen writer styles, struggling to isolate invariant style features (e.g., slant, stroke width, curvature) while ignoring irrelevant noise. To tackle this problem, we introduce Patch Contrastive Enhancement and Style-Aware Quantization via Denoising Diffusion (CONSTANT), a novel one-shot handwriting generation via diffusion model. CONSTANT leverages three key innovations: 1) a Style-Aware Quantization (SAQ) module that models style as discrete visual tokens capturing distinct concepts; 2) a contrastive objective to ensure these tokens are well-separated and meaningful in the embedding style space; 3) a latent patch-based contrastive (LLatentPCE) objective help improving quality and local structures by aligning multiscale spatial patches of generated and real features in latent space. Extensive experiments and analysis on benchmark datasets from multiple languages, including English, Chinese, and our proposed ViHTGen dataset for Vietnamese, demonstrate the superiority of adapting to new reference styles and producing highly detailed images of our method over state-of-the-art approaches. Code is available at GitHub

Related papers

• ScriptViT: Vision Transformer-Based Personalized Handwriting Generation [0.0]
  styled handwriting generation aims to synthesize handwritten text that looks both realistic and aligned with a specific writer's style.<n>We introduce a Vision Transformer-based style encoder that learns global stylistic patterns from multiple reference images.<n>We then integrate these style cues with the target text using a cross-attention mechanism, enabling the system to produce handwritten images that more faithfully reflect the intended style.
  arXiv  Detail & Related papers  (2025-11-23T06:38:23Z)
• Autoregressive Styled Text Image Generation, but Make it Reliable [51.09340470015673]
  This work is dedicated to developing strategies that reproduce the characteristics of a given writer, with promising results in terms of style fidelity and generalization achieved by the recently proposed Autoregressive Transformer paradigm for HTG.<n>In this work, we rethink the autoregressive by framing HTG as a multimodal prompt-conditioned generation task, tackling the content controllability issues by introducing special input tokens for better alignment with the visual ones.
  arXiv  Detail & Related papers  (2025-10-27T11:54:23Z)
• Qwen-Image Technical Report [86.46471547116158]
  We present Qwen-Image, an image generation foundation model that achieves significant advances in complex text rendering and precise image editing.<n>We design a comprehensive data pipeline that includes large-scale data collection, filtering, annotation, synthesis, and balancing.<n>Qwen-Image performs exceptionally well in alphabetic languages such as English, and also achieves remarkable progress on more challenging logographic languages like Chinese.
  arXiv  Detail & Related papers  (2025-08-04T11:49:20Z)
• Zero-Shot Chinese Character Recognition with Hierarchical Multi-Granularity Image-Text Aligning [52.92837273570818]
  Chinese characters exhibit unique structures and compositional rules, allowing for the use of fine-grained semantic information in representation.<n>We propose a Hierarchical Multi-Granularity Image-Text Aligning (Hi-GITA) framework based on a contrastive paradigm.<n>Our proposed Hi-GITA outperforms existing zero-shot CCR methods.
  arXiv  Detail & Related papers  (2025-05-30T17:39:14Z)
• StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation [24.588779332021137]
  multimodal autoregressive (AR) models have shown exceptional capabilities across various domains.<n>Style-aligned generation requires a reference style image and prompt, resulting in a text-image-to-image triplet.<n>We propose StyleAR, an innovative approach that combines a specially designed data curation method with our proposed AR models.
  arXiv  Detail & Related papers  (2025-05-26T12:01:15Z)
• Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models [76.68654868991517]
  Long-form text in images, such as paragraphs in slides or documents, remains a major challenge for current generative models.<n>We introduce a novel text-focused, binary tokenizer optimized for capturing detailed scene text features.<n>We develop ModelName, a multimodal autoregressive model that excels in generating high-quality long-text images with unprecedented fidelity.
  arXiv  Detail & Related papers  (2025-03-26T03:44:25Z)
• Towards Visual Text Design Transfer Across Languages [49.78504488452978]
  We introduce a novel task of Multimodal Style Translation (MuST-Bench) MuST-Bench is a benchmark designed to evaluate the ability of visual text generation models to perform translation across different writing systems. In response, we introduce SIGIL, a framework for multimodal style translation that eliminates the need for style descriptions.
  arXiv  Detail & Related papers  (2024-10-24T15:15:01Z)
• TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder [13.695128139074285]
  This paper addresses the challenge of one-shot personalization by mitigating overfitting, enabling the creation of controllable images through text prompts. We introduce three key techniques to enhance personalization performance: (1) augmentation tokens to encourage feature disentanglement and alleviate overfitting, (2) a knowledge-preservation loss to reduce language drift and promote generalizability across diverse prompts, and (3) SNR-weighted sampling for efficient training.
  arXiv  Detail & Related papers  (2024-09-12T17:47:51Z)
• Visual Style Prompting with Swapping Self-Attention [26.511518230332758]
  We propose a novel approach to produce a diverse range of images while maintaining specific style elements and nuances. During the denoising process, we keep the query from original features while swapping the key and value with those from reference features in the late self-attention layers. Our method demonstrates superiority over existing approaches, best reflecting the style of the references and ensuring that resulting images match the text prompts most accurately.
  arXiv  Detail & Related papers  (2024-02-20T12:51:17Z)
• Style Aligned Image Generation via Shared Attention [61.121465570763085]
  We introduce StyleAligned, a technique designed to establish style alignment among a series of generated images. By employing minimal attention sharing' during the diffusion process, our method maintains style consistency across images within T2I models. Our method's evaluation across diverse styles and text prompts demonstrates high-quality and fidelity.
  arXiv  Detail & Related papers  (2023-12-04T18:55:35Z)

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.