https://ym-xu.github.io/living-survey/fields/document-understanding/#tag=imagingDocument image processing and synthesis: dewarping, binarisation, layout and text generation.Thu, 12 Nov 2026 15:12:01 +0000https://arxiv.org/abs/2610.30863https://arxiv.org/abs/2610.30863Thu, 22 Oct 2026 00:00:00 +0000Yasas Savinda, Maheshi Buddhinee Dissanayake Historical document binarization remains challenging when faded ink, bleed-through, and background degradation exhibit wavelength-dependent behavior across visible and near-infrared observations. This study investigates whether adaptive cross-spectral feature fusion and targeted structural guidance can improve multispe…https://arxiv.org/abs/2610.27592https://arxiv.org/abs/2610.27592Tue, 20 Oct 2026 00:00:00 +0000Xingsong Ye, Yongkun Du, Jiaxin Zhang, Chong Sun, et al. · NeurIPS 2026 Aiming to modify textual content while preserving the original style, Scene Text Editing (STE) has significant practical value in many applications. STE typically requires paired images before and after editing for training. However, recent approaches rely heavily on synthetic paired data and complex disentanglement st…https://arxiv.org/abs/2610.23374https://arxiv.org/abs/2610.23374Fri, 16 Oct 2026 00:00:00 +0000MOSI. AI Recent closed-source image generation systems can produce diverse visual content from simple compositions to information-dense graphics, yet open-weight text-to-image models still struggle with dense text and intricate layouts. To narrow this gap, we introduce MOSS-Image, an open generation system that combines high-fi…https://arxiv.org/abs/2610.11286https://arxiv.org/abs/2610.11286Thu, 08 Oct 2026 00:00:00 +0000Feifei Li, Runjie Wang, Xiaohan Zhang, Zhenxing Qian, et al. The reliability and accountability of image generative models (IGMs) are essential for building responsible and trustworthy AI systems. Recent IGMs, such as Nano Banana and GPT-Image, now support complex instruction following, realistic image synthesis, and controllable scene-text rendering. As these capabilities expan…https://arxiv.org/abs/2610.01499https://arxiv.org/abs/2610.01499Thu, 01 Oct 2026 00:00:00 +0000Yu Huang, Jungang Li, Zhiyuan Wang, Yonghua Hei, et al. Recent video generation models can produce highly realistic videos from natural language instructions, with visual quality approaching cinematic standards. Existing evaluation benchmarks, however, predominantly assess visual quality, aesthetic appeal and physical plausibility, while paying limited attention to text, an…https://arxiv.org/abs/2609.40356https://arxiv.org/abs/2609.40356Wed, 30 Sep 2026 00:00:00 +0000Xinghao Chen, Xiangbo Gao, Jiongze Yu, Yuheng Wu, et al. · NeurIPS 2026 Recent video generation is increasingly realistic and controllable, yet video editing remains less developed, particularly for precise local edits that must preserve the original scene dynamics. Video scene text editing replaces text on scene surfaces, such as storefront signs, whiteboards, and product labels, while pr…https://arxiv.org/abs/2609.38636https://arxiv.org/abs/2609.38636Tue, 29 Sep 2026 00:00:00 +0000Nicolas Thiebaut, Nameer Hirschkind, Xiao Yu, Kyle Spence We introduce Scene Text Editing with Preserved Style (STEPS), a novel diffusion model architecture for quality text replacement in images. Scene Text Editing (STE), also known as Visual Text Editing, consists of changing the textual content in an image while conserving the original style, e.g. font, colors, orientation…https://arxiv.org/abs/2609.33758https://arxiv.org/abs/2609.33758Sun, 27 Sep 2026 00:00:00 +0000Sujal Burad, Aakanksha, A. N. Rajagopalan, Sumit Shekar Reliable document digitization in uncontrolled capture settings is challenging because real images exhibit multiple interacting degradations rather than a single isolated distortion. Documents thus captured are affected simultaneously by geometric distortions, like page warping, as well as photometric degradations such…https://arxiv.org/abs/2609.23953https://arxiv.org/abs/2609.23953Sun, 20 Sep 2026 00:00:00 +0000Simiao Ren, Ankit Raj, Tommy Duong, Yuxin Zhang, et al. AI agents that carry a multi-step computer task through on their own became ordinary tools in the past year, and the same autonomy is available to anyone whose task is harmful. We ask what that means for a relying party -- an insurer, a lender, an auditor -- whose evidence is a filed PDF. AgentForge-Bench measures how …https://arxiv.org/abs/2609.22916https://arxiv.org/abs/2609.22916Sat, 19 Sep 2026 00:00:00 +0000Guanqiao Chen, Jingru Tan, Dongxing Mao, Catherine Chen, et al. Generating text-rich images from prompts requires both textual fidelity and the coherent integration of text into the surrounding image. An explicit layout can provide structured guidance about what text should appear and where, but a well-formed plan alone does not guarantee that the renderer will realize it faithfull…https://arxiv.org/abs/2609.02349https://arxiv.org/abs/2609.02349Wed, 02 Sep 2026 00:00:00 +0000Qiang Xiang, Shuang Sun, Binglei Li, Yibo Chen, et al. Rendering accurate text remains difficult for image generation and editing models, especially when the target contains long, complex, and densely arranged text or rare characters. Existing approaches either improve native text rendering through stronger backbones and data-centric training without explicit glyph priors,…https://arxiv.org/abs/2608.18679https://arxiv.org/abs/2608.18679Wed, 19 Aug 2026 00:00:00 +0000Ayoub El Bouchtili, Guilhaume Leroy-Meline Structured documents such as invoices, forms, reports, and scientific articles derive meaning from the interplay between spatial layout, textual content, and logical structure. Generative models operating at the pixel or token level often struggle to capture these dependencies effectively. We explore FRAGMENT, a genera…https://arxiv.org/abs/2608.09536https://arxiv.org/abs/2608.09536Mon, 10 Aug 2026 00:00:00 +0000Lingming Su, Wanglong Lu, Tao Wang, Kaihao Zhang, et al. High-quality document images are pivotal for information archiving and downstream automatic processing. However, they are frequently compromised by diverse degradations during uncontrolled acquisition and transmission. While unified document restoration techniques have been proposed to restore images from multiple degr…https://arxiv.org/abs/2607.21936https://arxiv.org/abs/2607.21936Fri, 24 Jul 2026 00:00:00 +0000Gabeen Kim, Kyeongpil Kang · ACL 2026 Findings Historical documents act as invaluable knowledge archives but often suffer from illegibility due to physical deterioration and damage. While existing restoration methods based on masked language modeling effectively utilize local context, they struggle to restore named entities that require external historical knowledg…https://arxiv.org/abs/2607.16060https://arxiv.org/abs/2607.16060Fri, 17 Jul 2026 00:00:00 +0000Meijia Huang, Yingjie Yin, Shihao Wang, Chenguang Ma Artistic charts combine data visualization with expressive marks, textures, and typography, but they are difficult for image generators: an output is useful only when its stylization preserves chart geometry, exact in-image text, and the semantic binding between labels and marks. We introduce ArtChart, a framework for …https://arxiv.org/abs/2606.24333https://arxiv.org/abs/2606.24333Tue, 23 Jun 2026 00:00:00 +0000Jiahao Lyu, Pei Fu, Zhenhang Li, Shaojie Zhang, et al. · ECCV 2026 In-Image Machine Translation (IIMT) aims to translate scene text in an image and render the translated text back into the original regions while preserving the overall visual appearance. Recent unified multimodal models provide a promising solution by combining visual-text understanding and image generation within a si…https://arxiv.org/abs/2606.22625https://arxiv.org/abs/2606.22625Sun, 21 Jun 2026 00:00:00 +0000Sheng-Wei Chan, Jen-Shiun Chiang · ICDAR 2026 Workshop Degraded document image binarization is sensitive to domain shifts caused by paper aging, bleed-through, stains, shadows, and uneven illumination, and the foreground-background separation of recent learning-based methods can become unstable on unseen degradation domains. We propose DR-Mamba, a sample-conditioned detail…https://arxiv.org/abs/2606.11710https://arxiv.org/abs/2606.11710Wed, 10 Jun 2026 00:00:00 +0000Hsin-Jui Pan, Sheng-Wei Chan, Jen-Shiung Chiang This paper presents ERN-Net, an Evolving Reason Node-Net for efficient document image binarization. ERN-Net enhances degradation-sensitive regions, such as faint strokes, broken characters, and noisy backgrounds, through evolving reason nodes and multi-scale reasoning. We further compare ResNet-101, ConvNeXt-Tiny, and …https://arxiv.org/abs/2606.08781https://arxiv.org/abs/2606.08781Sun, 07 Jun 2026 00:00:00 +0000Sheng-Wei Chan, Yung-Che Wang, Hsin-Jui Pan, Chia-Min Lin, et al. Document image binarization must preserve thin, broken, and low-contrast strokes against degraded backgrounds; Mamba-based state space models have so far been explored only preliminarily for it. We measure what state-space propagation does to document features and find that it does not attenuate foreground responses: e…https://arxiv.org/abs/2606.05730https://arxiv.org/abs/2606.05730Thu, 04 Jun 2026 00:00:00 +0000Shuyu Wang, Zhile Guan, Hongxiu Chen, Yule Duan, et al. We propose TextWand, a general-purpose framework that unifies scene text removal, generation, and replacement into a single model. By decomposing complex editing tasks into the atomic primitives of rendering and erasure, TextWand achieves precise control over both text appearance and background integrity. Specifically,…https://arxiv.org/abs/2606.01472https://arxiv.org/abs/2606.01472Sun, 31 May 2026 00:00:00 +0000Nataraj Agaram Sundar, Tejas Morabia High-stakes production document-generation systems require language models to be adaptive, evidence-grounded, and auditable. We present HOPM, a hierarchical online prompt mutation framework evaluated on a real marketplace dispute-evidence workflow. HOPM treats prompts as online policies: a family/version router selects…https://arxiv.org/abs/2605.21090https://arxiv.org/abs/2605.21090Wed, 20 May 2026 00:00:00 +0000Yiheng Lin, Siyu Jiao, Xiaohan Lan, Wei Zhou, et al. Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editing remains challenging, as it requires models to precisely modify textual content while preserving visual realism and non-target regions. Cu…https://arxiv.org/abs/2605.19688https://arxiv.org/abs/2605.19688Tue, 19 May 2026 00:00:00 +0000Kylian Ronfleux-Corail, Guillaume Bernard, Mickaël Coustaty, Nicolas Sidère · ICDAR 2026 Document manipulation localization models achieve strong performance on public benchmarks yet fail to generalize to operational document workflows. We identify a critical and overlooked source of this gap: the mismatch between the narrow distribution of JPEG quantization tables used during training -restricted to stand…https://arxiv.org/abs/2605.15523https://arxiv.org/abs/2605.15523Fri, 15 May 2026 00:00:00 +0000Hongxi Li, Tong Wang, Chengjing Wu, Tianbao Liu, et al. · ICML 2026 Scene text editing aims to modify text in a target region of an image while preserving surrounding background style and texture. Existing methods rely solely on image background information while neglecting the visual details of target regions, which discards stylistic features in the original text and essentially degr…