arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.09484cs.CV
收藏

基于组件意识的草图到图像生成:使用自注意力编码和坐标保持融合

Component-Aware Sketch-to-Image Generation Using Self-Attention Encoding and Coordinate-Preserving Fusion

Ali Zia, Muhammad Umer Ramzan, Usman Ali, Muhammad Faheem, Abdelwahed Khamis, Shahnawaz Qureshi

AI总结:

本文提出了一种基于自注意力编码和坐标保持融合的组件意识框架,用于提升草图到图像生成的逼真度和一致性。

摘要:

将自由手绘草图转换为逼真图像仍然是图像合成中的基本挑战,尤其是在草图抽象、稀疏且风格多样的情况下。现有方法,包括基于GAN和扩散模型的方法,往往难以重建细节,保持空间对齐或适应不同草图领域。在本文中,我们提出了一种组件意识的自完善框架,用于草图到图像生成,通过新颖的两阶段架构来解决这些挑战。首先,一个基于自注意力的自动编码网络(SA2N)从组件级草图区域中捕获局部语义和结构特征,而一个坐标保持门控融合模块(CGF)将这些特征整合到连贯的空间布局中。最后,一个基于修改后的StyleGAN2骨干网络构建的时空自适应细化修订器(SARR),通过由空间上下文引导的迭代细化来增强真实感和一致性。在面部(CelebAMask-HQ,CUFSF)和非面部(Sketchy,ChairsV2,ShoesV2)数据集上的广泛实验证明了我们方法的鲁棒性和通用性。所提出的框架在多个数据集上均优于最先进的GAN和扩散模型,实现了图像保真度、语义准确性和感知质量的显著提升。在CelebAMask-HQ上,我们的模型在FID、IS、KID和SSIM上分别比先前方法提高了21%、58%、41%和20%。这些结果,加上在不同领域中更高的效率和视觉一致性,使我们的方法成为应用于刑侦、数字艺术修复和一般基于草图的图像合成中的有力候选。

英文摘要:

Translating freehand sketches into photorealistic images remains a fundamental challenge in image synthesis, particularly due to the abstract, sparse, and stylistically diverse nature of sketches. Existing approaches, including GAN-based and diffusion-based models, often struggle to reconstruct fine-grained details, maintain spatial alignment, or adapt across different sketch domains. In this paper, we propose a component-aware, self-refining framework for sketch-to-image generation that addresses these challenges through a novel two-stage architecture. A Self-Attention-based Autoencoder Network (SA2N) first captures localised semantic and structural features from component-wise sketch regions, while a Coordinate-Preserving Gated Fusion (CGF) module integrates these into a coherent spatial layout. Finally, a Spatially Adaptive Refinement Revisor (SARR), built on a modified StyleGAN2 backbone, enhances realism and consistency through iterative refinement guided by spatial context. Extensive experiments across both facial (CelebAMask-HQ, CUFSF) and non-facial (Sketchy, ChairsV2, ShoesV2) datasets demonstrate the robustness and generalizability of our method. The proposed framework consistently outperforms state-of-the-art GAN and diffusion models, achieving significant gains in image fidelity, semantic accuracy, and perceptual quality. On CelebAMask-HQ, our model improves over prior methods by 21% (FID), 58% (IS), 41% (KID), and 20% (SSIM). These results, along with higher efficiency and visual coherence across diverse domains, position our approach as a strong candidate for applications in forensics, digital art restoration, and general sketch-based image synthesis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑