UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy

• URL: http://arxiv.org/abs/2510.13745v1
• Date: Wed, 15 Oct 2025 16:52:07 GMT
• Title: UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy
• Abstract summary: We introduce textbfUniCalli, a unified diffusion framework for column-level recognition and generation.<n>We curated a dataset of over 8,000 digitized pieces, with 4,000 annotated pieces, trained on a mix of synthetic, labeled, and unlabeled data.<n>The model achieves state-of-the-art generative quality with superior ligature continuity and layout fidelity, alongside stronger recognition.
• Score: 37.162115015010585
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Computational replication of Chinese calligraphy remains challenging. Existing methods falter, either creating high-quality isolated characters while ignoring page-level aesthetics like ligatures and spacing, or attempting page synthesis at the expense of calligraphic correctness. We introduce \textbf{UniCalli}, a unified diffusion framework for column-level recognition and generation. Training both tasks jointly is deliberate: recognition constrains the generator to preserve character structure, while generation provides style and layout priors. This synergy fosters concept-level abstractions that improve both tasks, especially in limited-data regimes. We curated a dataset of over 8,000 digitized pieces, with ~4,000 densely annotated. UniCalli employs asymmetric noising and a rasterized box map for spatial priors, trained on a mix of synthetic, labeled, and unlabeled data. The model achieves state-of-the-art generative quality with superior ligature continuity and layout fidelity, alongside stronger recognition. The framework successfully extends to other ancient scripts, including Oracle bone inscriptions and Egyptian hieroglyphs. Code and data can be viewed in \href{https://github.com/EnVision-Research/UniCalli}{this URL}.

Related papers

• CalliMaster: Mastering Page-level Chinese Calligraphy via Layout-guided Spatial Planning [37.872480365351485]
  Page-level calligraphy synthesis requires balancing glyph precision with layout composition.<n>We present textbfCalliMaster, a unified framework for controllable generation and editing.
  arXiv  Detail & Related papers  (2026-03-12T22:01:19Z)
• Generative Data Transformation: From Mixed to Unified Data [57.84692191369066]
  textscTaesar is a emphdata-centric framework for textbftarget-textbfal textbfregeneration.<n>It encodes cross-domain context into target sequences, enabling standard models to learn intricate dependencies without complex fusion architectures.
  arXiv  Detail & Related papers  (2026-02-26T08:30:09Z)
• Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer [50.69959748410398]
  We introduce MingTok, a new family of visual tokenizers with a continuous latent space for unified autoregressive generation and understanding.<n>MingTok adopts a three-stage sequential architecture involving low-level encoding, semantic expansion, and visual reconstruction.<n>Built on top of it, Ming-UniVision eliminates the need for task-specific visual representations, and unifies diverse vision-language tasks under a single autoregrsssive prediction paradigm.
  arXiv  Detail & Related papers  (2025-10-08T02:50:14Z)
• Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation [120.23172120151821]
  We propose a novel approach for disentangling visual and semantic features from the backbones of pre-trained diffusion models.<n>We introduce an automated pipeline that constructs image pairs with annotated semantic and visual correspondences.<n>We propose a new metric, Visual Semantic Matching, that quantifies visual inconsistencies in subject-driven image generation.
  arXiv  Detail & Related papers  (2025-09-26T07:11:55Z)
• A Transformer Based Handwriting Recognition System Jointly Using Online and Offline Features [8.419663258260671]
  We introduce an end-to-end network that performs early fusion of offline images and online stroke data.<n>Our approach achieves state-of-the-art accuracy, exceeding previous bests by up to 1%.
  arXiv  Detail & Related papers  (2025-06-25T08:58:47Z)
• Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations [33.11867433769496]
  This paper presents a framework that attempts to unify visual understanding and generation within a shared semantic representation.<n>At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete tokens using a text-aligned codebook projected from a large language model's (LLM) vocabulary.<n> Experiments across benchmarks show that Tar matches or surpasses existing multimodal LLM methods, achieving faster convergence and greater training efficiency.
  arXiv  Detail & Related papers  (2025-06-23T17:59:14Z)
• Bridging Textual-Collaborative Gap through Semantic Codes for Sequential Recommendation [91.13055384151897]
  CCFRec is a novel Code-based textual and Collaborative semantic Fusion method for sequential Recommendation.<n>We generate fine-grained semantic codes from multi-view text embeddings through vector quantization techniques.<n>In order to further enhance the fusion of textual and collaborative semantics, we introduce an optimization strategy.
  arXiv  Detail & Related papers  (2025-03-15T15:54:44Z)
• An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction [4.194768796374315]
  We propose a novel method for joint entity and relation extraction from unstructured text by framing it as a conditional sequence generation problem. It generates a linearized graph where nodes represent text spans and edges represent relation triplets. Our method employs a transformer encoder-decoder architecture with pointing mechanism on a dynamic vocabulary of spans and relation types.
  arXiv  Detail & Related papers  (2024-01-02T18:32:14Z)
• DeepCalliFont: Few-shot Chinese Calligraphy Font Synthesis by Integrating Dual-modality Generative Models [20.76773399161289]
  Few-shot font generation, especially for Chinese calligraphy fonts, is a challenging and ongoing problem. We propose a novel model, DeepCalliFont, for few-shot Chinese calligraphy font synthesis by integrating dual-modality generative models.
  arXiv  Detail & Related papers  (2023-12-16T04:23:12Z)
• Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets [56.018551958004814]
  This paper addresses the task of generating fluent descriptions by training on a non-uniform combination of data sources. Large-scale datasets with noisy image-text pairs provide a sub-optimal source of supervision. We propose to leverage and separate semantics and descriptive style through the incorporation of a style token and keywords extracted through a retrieval component.
  arXiv  Detail & Related papers  (2021-11-24T19:00:05Z)

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.