papers

Publications (20)

cs.CV2026

NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild

Aleksandr Gushchin, Khaled Abud, Ekaterina Shumitskaya +51

This paper presents an overview of the NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild, held in conjunction with the NTIRE workshop at CVPR 2026. The goal o…

cs.CV2025

Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration

Yuyi Zhang, Peirong Zhang, Zhenhua Yang +5

Historical documents represent an invaluable cultural heritage, yet have undergone significant degradation over time through tears, water erosion, and oxidation. Existing Historica…

cs.CV2025

DocIQ: A Benchmark Dataset and Feature Fusion Network for Document Image Quality Assessment

Zhichao Ma, Fan Huang, Lu Zhao +3

Document image quality assessment (DIQA) is an important component for various applications, including optical character recognition (OCR), document restoration, and the evaluation…

cs.CV2022

Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context

Chongyu Liu, Lianwen Jin, Yuliang Liu +4

Text removal has attracted increasingly attention due to its various applications on privacy protection, document restoration, and text editing. It has shown significant progress w…

cs.CV2026

NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results

Zheng Chen, Kai Liu, Jue Gong +108

This paper presents the NTIRE 2025 image super-resolution (4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to r…

cs.CV2026

LOGER: Local--Global Ensemble for Robust Deepfake Detection in the Wild

Fei Wu, Dagong Lu, Mufeng Yao +2

Robust deepfake detection in the wild remains challenging due to the ever-growing variety of manipulation techniques and uncontrolled real-world degradations. Forensic cues for dee…

cs.CV2026

PosterVerse: A Full-Workflow Framework for Commercial-Grade Poster Generation with HTML-Based Scalable Typography

Junle Liu, Peirong Zhang, Yuyi Zhang +5

Commercial-grade poster design demands the seamless integration of aesthetic appeal with precise, informative content delivery. Current automated poster generation systems face sig…

cs.CV2026

Robust Deepfake Detection, NTIRE 2026 Challenge: Report

Benedikt Hopf, Radu Timofte, Chenfan Qu +54

Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under exposure to even slight imag…

cs.CV2025

Revisiting Tampered Scene Text Detection in the Era of Generative AI

Chenfan Qu, Yiwu Zhong, Fengjun Guo +1

The rapid advancements of generative AI have fueled the potential of generative text image editing, meanwhile escalating the threat of misinformation spreading. However, existing f…

cs.CV2022

Inharmonious Region Localization by Magnifying Domain Discrepancy

Jing Liang, Li Niu, Penghao Wu +2

Inharmonious region localization aims to localize the region in a synthetic image which is incompatible with surrounding background. The inharmony issue is mainly attributed to the…

cs.CV2021

Visible Watermark Removal via Self-calibrated Localization and Background Refinement

Jing Liang, Li Niu, Fengjun Guo +2

Superimposing visible watermarks on images provides a powerful weapon to cope with the copyright issue. Watermark removal techniques, which can strengthen the robustness of visible…

cs.CV2023

Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation

Li Niu, Linfeng Tan, Xinhao Tao +4

Given a composite image, image harmonization aims to adjust the foreground illumination to be consistent with background. Previous methods have explored transforming foreground fea…

cs.CV2026

HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild

Fei Wu, Dagong Lu, Mufeng Yao +2

Robust detection of AI-generated images in the wild remains challenging due to the rapid evolution of generative models and varied real-world distortions. We argue that relying on…

cs.CV2026

NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods

Jie Cai, Kangning Yang, Zhiyuan Li +50

In this paper, we review the NTIRE 2026 challenge on single-image reflection removal (SIRR) in the wild. SIRR is a fundamental task in image restoration. Despite progress in academ…

cs.CV2022

Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild

Jiaxin Zhang, Canjie Luo, Lianwen Jin +2

Camera-captured document images usually suffer from perspective and geometric deformations. It is of great value to rectify them when considering poor visual aesthetics and the det…

cs.CV2024

SemanticMIM: Marring Masked Image Modeling with Semantics Compression for General Visual Representation

Yike Yuan, Huanzhang Dou, Fengjun Guo +1

This paper represents a neat yet effective framework, named SemanticMIM, to integrate the advantages of masked image modeling (MIM) and contrastive learning (CL) for general visual…

cs.CV2023

DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures

Jiaxin Zhang, Bangdong Chen, Hiuyi Cheng +3

Recently, there has been a growing interest in research concerning document image analysis and recognition in photographic scenarios. However, the lack of labeled datasets for this…

cs.CV2025

Omni-IML: Towards Unified Image Manipulation Localization

Chenfan Qu, Yiwu Zhong, Fengjun Guo +1

Existing Image Manipulation Localization (IML) methods mostly rely heavily on task-specific designs, making them perform well only on the target IML task, while joint training on m…

cs.CV2026

UPOCR: Towards Unified Pixel-Level OCR Interface

Dezhi Peng, Zhenhua Yang, Jiaxin Zhang +5

Existing optical character recognition (OCR) methods rely on task-specific designs with divergent paradigms, architectures, and training strategies, which significantly increases t…

cs.CV2024

Leveraging Text Localization for Scene Text Removal via Text-aware Masked Image Modeling

Zixiao Wang, Hongtao Xie, YuXin Wang +3

Existing scene text removal (STR) task suffers from insufficient training data due to the expensive pixel-level labeling. In this paper, we aim to address this issue by introducing…