针对屏幕内容图像畸变，提出结构纹理增强网络与自估计校正机制。
Unwarping Screen Content Images via Structure-texture Enhancement Network and Transformation Self-estimation
- 分结构与纹理双分支，结合B样条隐式表示增强细节建模。
- 自估计模块可自动检测并修正坐标变换误差，提升真实场景适应性。
- 在屏幕内容图像上显著优于现有方法，也适用于自然图像去畸变。
现有基于隐式神经网络的图像去畸变方法在自然图像上表现良好，但在处理屏幕内容图像（SCIs）时效果不佳，因后者常包含大范围几何畸变、文字、符号和锐利边缘。为此，本文提出结构-纹理增强网络（STEN）结合变换自估计机制以应对SCI畸变问题。STEN包含一个B样条隐式神经表示模块和一个变换误差估计与自校正算法。其由两个分支构成：结构估计分支（SEB）增强局部聚合与全局依赖建模；纹理估计分支（TEB）利用B样条隐式神经表示提升纹理细节合成能力。此外，变换自估计模块能自主估计变换误差并修正坐标变换矩阵，有效应对真实世界图像畸变。在公开SCI数据集上的大量实验表明，本方法显著优于当前最优方法；在知名自然图像数据集上的对比也展示了其在自然图像去畸变方面的潜力。
原文摘要 · Abstract (English)
While existing implicit neural network-based image unwarping methods perform well on natural images, they struggle to handle screen content images (SCIs), which often contain large geometric distortions, text, symbols, and sharp edges. To address this, we propose a structure-texture enhancement network (STEN) with transformation self-estimation for SCI warping. STEN integrates a B-spline implicit neural representation module and a transformation error estimation and self-correction algorithm. It comprises two branches: the structure estimation branch (SEB), which enhances local aggregation and global dependency modeling, and the texture estimation branch (TEB), which improves texture detail synthesis using B-spline implicit neural representation. Additionally, the transformation self-estimation module autonomously estimates the transformation error and corrects the coordinate transformation matrix, effectively handling real-world image distortions. Extensive experiments on public SCI datasets demonstrate that our approach significantly outperforms state-of-the-art methods. Comparisons on well-known natural image datasets also show the potential of our approach for natural image distortion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。