用半超分GAN修复严重损坏图像，提升恢复质量。
Image inpainting for corrupted images by using the semi-super resolution GAN
- 提出半超分GAN（SSRGAN），融合修复与超分能力。
- 在多数据集上验证，对高程度像素缺失仍能生成高质量图像。
- 适合图像修复、老照片复原等需要高保真重建的场景。
图像修复是提升受损图像质量的重要技术。本研究的核心挑战在于模型需处理输入图像中不同程度的损坏。为此，我们引入一种生成对抗网络（GAN），用于学习并重建缺失像素。此外，我们提出了一种独特的超分辨率生成对抗网络（SRGAN）变体，称为半超分生成对抗网络（SSRGAN）。通过三个不同数据集评估了所提模型的鲁棒性与准确性。训练过程中，采用多种像素损坏程度以实现最佳精度，并生成高质量图像。
原文摘要 · Abstract (English)
Image inpainting is a valuable technique for enhancing images that have been corrupted. The primary challenge in this research revolves around the extent of corruption in the input image that the deep learning model must restore. To address this challenge, we introduce a Generative Adversarial Network (GAN) for learning and replicating the missing pixels. Additionally, we have developed a distinct variant of the Super-Resolution GAN (SRGAN), which we refer to as the Semi-SRGAN (SSRGAN). Furthermore, we leveraged three diverse datasets to assess the robustness and accuracy of our proposed model. Our training process involves varying levels of pixel corruption to attain optimal accuracy and generate high-quality images.
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。