ARIN：面向敦煌洞窟壁画鲁棒盲修复的自适应重采样与实例归一化方法
ARIN: Adaptive Resampling and Instance Normalization for Robust Blind Inpainting of Dunhuang Cave Paintings
AI总结：
本文提出 ARIN 网络，通过自适应重采样与实例归一化并结合 CAR 与 HINet，实现对敦煌洞窟壁画的鲁棒盲修复，尤其对高斯噪声具有强鲁棒性，性能与敦煌挑战赛第一名相当。
摘要：
图像增强算法对于现实世界计算机视觉任务非常有用，在这些任务中，图像分辨率往往受到传感器尺寸的物理限制。虽然最先进的深度神经网络在图像增强方面表现出令人印象深刻的结果，但它们往往难以增强现实世界图像。在这项工作中，我们处理一个现实世界场景：敦煌洞窟图像的修复。敦煌数据集由壁画组成，其中一半遭受腐蚀和老化。这些壁画具有丰富的内容，如佛像、菩萨、供养人、建筑、舞蹈、音乐以及由跨越十个世纪的不同艺术家设计的装饰图案，这使得人工修复具有挑战性。我们修改了两种不同的现有方法（CAR、HINet），它们基于最先进（SOTA）的超分辨率和去模糊网络。我们表明这些方法能够成功修复和增强这些受损的洞窟壁画。我们进一步表明，CAR 和 HINet 的一种新颖组合，即我们提出的修复网络（ARIN），对外部噪声，尤其是高斯噪声，具有很强的鲁棒性。为此，我们将所提出的方法与现有 SOTA 网络以及敦煌挑战赛获胜者进行了定量和定性比较。所提出的方法之一（HINet）代表了新的最先进水平，并优于敦煌挑战赛的第一名，而我们的组合 ARIN 对噪声具有鲁棒性，与第一名相当。我们还展示并讨论了定性结果，显示我们的方法对敦煌洞窟图像修复的影响。
英文摘要：
Image enhancement algorithms are very useful for real world computer vision tasks where image resolution is often physically limited by the sensor size. While state-of-the-art deep neural networks show impressive results for image enhancement, they often struggle to enhance real-world images. In this work, we tackle a real-world setting: inpainting of images from Dunhuang caves. The Dunhuang dataset consists of murals, half of which suffer from corrosion and aging. These murals feature a range of rich content, such as Buddha statues, bodhisattvas, sponsors, architecture, dance, music, and decorative patterns designed by different artists spanning ten centuries, which makes manual restoration challenging. We modify two different existing methods (CAR, HINet) that are based upon state-of-the-art (SOTA) super resolution and deblurring networks. We show that those can successfully inpaint and enhance these deteriorated cave paintings. We further show that a novel combination of CAR and HINet, resulting in our proposed inpainting network (ARIN), is very robust to external noise, especially Gaussian noise. To this end, we present a quantitative and qualitative comparison of our proposed approach with existing SOTA networks and winners of the Dunhuang challenge. One of the proposed methods HINet) represents the new state of the art and outperforms the 1st place of the Dunhuang Challenge, while our combination ARIN, which is robust to noise, is comparable to the 1st place. We also present and discuss qualitative results showing the impact of our method for inpainting on Dunhuang cave images.
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。
