ARIN: Adaptive Resampling and Instance Normalization for Robust Blind Inpainting of Dunhuang Cave Paintings

arXiv:2402.16188v1 Announce Type: new
Abstract: 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 …

abstract algorithms art arxiv blind computer computer vision cs.cv image images inpainting instance networks neural networks normalization resampling results robust sensor show state struggle tasks type vision world