Ancient mural inpainting via structure information guided two-branch model

نویسندگان

چکیده

Abstract Ancient murals are important cultural heritages for our exploration of ancient civilizations and great research value. Due to long-time exposure the environment, often suffer from damage (deterioration) such as cracks, scratches, corrosion, paint loss, even large-region falling off. It is an urgent work protect restore these damaged murals. Mural inpainting techniques refer virtually filling deteriorated regions by reconstructing structure texture elements mural images. Most existing approaches fail fill loss contents that contain complex structures diverse patterns since they neglect importance guidance. In this paper, we propose a structure-guided two-branch model based on generative adversarial network (GAN) inpainting. proposed model, process can be divided into two stages: reconstruction content restoration. These stages conducted using (SRN) restoration (CRN), respectively. stage, SRN employs Gated Convolution Fast Fourier (FFC) residual block reconstruct missing CRN uses (generated SRN) guide We design parallel encoder improve color quality Moreover, cascade attention module capture long-term relevance information in deep features. helps alleviate texture-blur color-bias problem. conduct experiments both simulated real murals, compare results with other four competitive approaches. Experimental show outperforms terms clarity, consistency structural continuity restored addition, achieve comparatively high quantitative evaluation metrics.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Structure guided fusion for depth map inpainting

0167-8655/$ see front matter 2012 Elsevier B.V. A http://dx.doi.org/10.1016/j.patrec.2012.06.003 ⇑ Corresponding author. E-mail addresses: [email protected] (F. Qi), gmshi@x 1 Principal corresponding author. Depth acquisition becomes inexpensive after the revolutionary invention of Kinect. For computer vision applications, depth maps captured by Kinect require additional processing to fill up mi...

متن کامل

Inpainting of Ancient Austrian frescoes

Digital inpainting methods provide an important tool in the restoration of images in a wide range of applications. We present mathematical methods with certain higher order partial differential equations for the inpainting of ancient frescoes. In particular we discuss the Cahn-Hilliard equation for the inpainting of binary structure and a higher order total variation approach. As an example for...

متن کامل

Geometrically Guided Exemplar-Based Inpainting

Exemplar-based methods have proven their efficiency for the reconstruction of missing parts in a digital image. Texture as well as local geometry are often very well restored. Some applications, however, require the ability to reconstruct non local geometric features, e.g. long edges. We propose in this paper to endow a particular instance of exemplar-based method with a geometric guide. The gu...

متن کامل

Object Removal by Depth-guided Inpainting∗

Object removal by image inpainting aims at the visual uniformity of the inpainted blanks among their surroundings. Most inpainting algorithms pursue the structure continuity and texture similarity only in color. In this paper we take the view depth continuity into account and propose a depth-guided inpainting algorithm, in which a single color image and its associated disparity map are inpainte...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Heritage Science

سال: 2023

ISSN: ['2050-7445']

DOI: https://doi.org/10.1186/s40494-023-00972-x