arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01431cs.CV
收藏

用于高分辨率图像修复的聚合上下文变换

Aggregated Contextual Transformations for High-Resolution Image Inpainting

Microsoft Research(微软研究院);School of Computer, Sun Yat-sen University(中山大学计算机学院)

Yanhong Zeng, Jianlong Fu, Hongyang Chao, Baining Guo

AI总结:

本文提出AOT-GAN,通过多感受野上下文变换聚合与掩码预测判别任务解决高分辨率图像修复中的结构推理和纹理合成问题,并在Places2及实际应用中验证其优势。

摘要:

最先进的图像修复方法在高分辨率图像(例如512×512)中可能会生成扭曲的结构和模糊的纹理。这些挑战主要源于:(1)从远距离上下文中推理图像内容;(2)为大面积缺失区域合成细粒度纹理。为克服这两个挑战,我们提出了一种增强的基于GAN的模型,名为聚合上下文变换GAN(Aggregated COntextual-Transformation GAN,AOT-GAN),用于高分辨率图像修复。具体而言,为增强上下文推理,我们通过堆叠多层所提出的AOT块来构建AOT-GAN的生成器。AOT块聚合来自各种感受野的上下文变换,从而能够同时捕获有信息的远距离图像上下文和丰富的感兴趣模式,以进行上下文推理。为改进纹理合成,我们通过使用定制的掩码预测任务训练AOT-GAN的判别器来增强该判别器。这样的训练目标迫使判别器区分真实图像块与合成图像块的详细外观,进而促进生成器合成清晰纹理。在Places2上进行的大量比较表明,我们的模型在FID方面显著优于最先进方法,相对改进达38.60%;Places2是最具挑战性的基准,包含涵盖365个复杂场景的180万张高分辨率图像。一项包含30多名受试者的用户研究进一步验证了AOT-GAN的优越性。我们还在标志移除、人脸编辑和物体移除等实际应用中评估了所提出的AOT-GAN。结果表明,我们的模型在现实世界中实现了富有前景的补全效果。我们在https://github.com/researchmm/AOT-GAN-for-Inpainting发布了代码和模型。

英文摘要:

State-of-the-art image inpainting approaches can suffer from generating distorted structures and blurry textures in high-resolution images (e.g., 512x512). The challenges mainly drive from (1) image content reasoning from distant contexts, and (2) fine-grained texture synthesis for a large missing region. To overcome these two challenges, we propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN), for high-resolution image inpainting. Specifically, to enhance context reasoning, we construct the generator of AOT-GAN by stacking multiple layers of a proposed AOT block. The AOT blocks aggregate contextual transformations from various receptive fields, allowing to capture both informative distant image contexts and rich patterns of interest for context reasoning. For improving texture synthesis, we enhance the discriminator of AOT-GAN by training it with a tailored mask-prediction task. Such a training objective forces the discriminator to distinguish the detailed appearances of real and synthesized patches, and in turn, facilitates the generator to synthesize clear textures. Extensive comparisons on Places2, the most challenging benchmark with 1.8 million high-resolution images of 365 complex scenes, show that our model outperforms the state-of-the-art by a significant margin in terms of FID with 38.60% relative improvement. A user study including more than 30 subjects further validates the superiority of AOT-GAN. We further evaluate the proposed AOT-GAN in practical applications, e.g., logo removal, face editing, and object removal. Results show that our model achieves promising completions in the real world. We release code and models in https://github.com/researchmm/AOT-GAN-for-Inpainting.

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。

↑