用生成先验和几何对称性修复广角人像畸变，效果更自然。
Combining Generative and Geometry Priors for Wide-Angle Portrait Correction
- 引入生成式人脸先验与背景对称性约束协同校正
- 在直线度、形状一致性等指标上显著优于现有方法
- 适合图像修复、摄影增强领域的研究与应用
广角镜头在人像摄影中常导致严重畸变，尤其影响面部区域。本文提出将生成式人脸先验建模为引导的自然流形，用于指导面部校正。同时发现非人脸背景存在显著中心对称性，但此前未被用于校正过程。为此，我们引入一种新约束，显式强制对称性，提升非人脸区域的视觉自然性。实验表明，本方法在直线度、形状一致性等量化指标上大幅超越先前方法，并在主观视觉质量上表现优异。所有代码与模型已开源于 https://github.com/Dev-Mrha/DualPriorsCorrection。
原文摘要 · Abstract (English)
Wide-angle lens distortion in portrait photography presents a significant challenge for capturing photo-realistic and aesthetically pleasing images. Such distortions are especially noticeable in facial regions. In this work, we propose encapsulating the generative face prior as a guided natural manifold to facilitate the correction of facial regions. Moreover, a notable central symmetry relationship exists in the non-face background, yet it has not been explored in the correction process. This geometry prior motivates us to introduce a novel constraint to explicitly enforce symmetry throughout the correction process, thereby contributing to a more visually appealing and natural correction in the non-face region. Experiments demonstrate that our approach outperforms previous methods by a large margin, excelling not only in quantitative measures such as line straightness and shape consistency metrics but also in terms of perceptual visual quality. All the code and models are available at https://github.com/Dev-Mrha/DualPriorsCorrection.
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。