Imaging Novecento. A Mobile App for Automatic Recognition of Artworks and Transfer of Artistic Styles

Becattini, Federico; Ferracani, Andrea; Landucci, Lea; Pezzatini, Daniele; Uricchio, Tiberio; Bimbo, Alberto Del

doi:10.1007/978-3-319-48496-9_62

Cited by 17 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The style loss L S is computed as Eqn. (3). As the styles of traditional Chinese artworks are often textueless and lack of color information, we strengthen the effects of style transfer by using more low-level and high-level layers for style reconstruction than [10].…”

Section: Network Architecturementioning

confidence: 91%

“…Recently, convolutional neural network (CNN) [13] based style transfer methods have shown successful applications in transferring the style of a certain type of artistic painting, e.g, Vincent van Gogh's "The Starry Night", to a real world photograph, e.g., an image taken by iPhone. Since the seminal work of Gatys et al [7], it has attracted a lot of attentions from both academia [10,15,23,24,8,28,31,6,5,4] and industry [26,1,11,3]. Although the work of neural style transfer has shown promising progress on transferring artistic images with rich textures and colors, e.g., the oil paintings, we observe that it is less effective in transferring Chinese traditional painting.…”

Section: Introductionmentioning

confidence: 91%

See 1 more Smart Citation

Neural Abstract Style Transfer for Chinese Traditional Painting

Xiong

et al. 2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

Chinese traditional painting is one of the most historical artworks in the world. It is very popular in Eastern and Southeast Asia due to being aesthetically appealing. Compared with western artistic painting, it is usually more visually abstract and textureless. Recently, neural network based style transfer methods have shown promising and appealing results which are mainly focused on western painting. It remains a challenging problem to preserve abstraction in neural style transfer. In this paper, we present a Neural Abstract Style Transfer method for Chinese traditional painting. It learns to preserve abstraction and other style jointly end-to-end via a novel MXDoG-guided filter (Modified version of the eXtended Difference-of-Gaussians) and three fully differentiable loss terms. To the best of our knowledge, there is little work study on neural style transfer of Chinese traditional painting. To promote research on this direction, we collect a new dataset with diverse photo-realistic images and Chinese traditional paintings 6 . In experiments, the proposed method shows more appealing stylized results in transferring the style of Chinese traditional painting than state-of-the-art neural style transfer methods.

show abstract

Section: Network Architecturementioning

confidence: 91%

Section: Introductionmentioning

confidence: 91%

Neural Abstract Style Transfer for Chinese Traditional Painting

Xiong

et al. 2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

show abstract

“…Archaeological sites, museums and art collections have long begun to rely on these technologies also to increase the involvement of the viewer and to offer more complete knowledge of what is observed. Interactive monitors, 3D printing, mobile applications, consoles with threedimensional reconstructions and augmented reality, therefore, aim to increase interest in culture in an innovative way (Ballarin, Balletti & Vernier;2018;Fernández-Palacios, Morabito & Remondino, 2017;Becattini et al, 2016). These technologies have also allowed exhibiting objects from collections that cannot normally be shown due to fragility or limited space available.…”

Section: Recent Technological Advances For Ch Sites (State Of Art)mentioning

confidence: 99%

Accessibility to Underwater Cultural Heritage: Interactive Web Navigation of the Roman Submersed Vessel of Cala Minnola

Scianna

Gaglio

Guardia

2021

Proceedings ARQUEOLÓGICA 2.0 - 9th International Congress &Amp; 3rd GEORES - GEOmatics and pREServation

View full text Add to dashboard Cite

The possibilities offered by photogrammetric reconstruction based on computer vision algorithms allowed in recent years to develop new interesting solutions for the use and dissemination of knowledge on Cultural Heritage (CH). In the same way, the recent technological development in the field of Virtual Reality (VR) has offered new possibilities for the creation of interactive virtual environments which can be freely accessed via the browser using any type of device. These technologies acquire an additional relevance if applied to archaeological sites or monuments that are difficult to access, or even totally inaccessible, except by specialized personnel. In this case the virtual fruition on web becomes strategic for the valorization of CH, as in the case of submerged archaeological sites, where the virtual tour represents in fact the only opportunity of diffuse accessibility. The present case shows the virtual reconstruction of the wreck area of the Roman ship found on the seabed of Cala Minnola on the island of Levanzo (TP, Italy). The model, obtained from a Structure from Motion (SfM) processing of a chunk of photos originally intended for a traditional photogrammetric survey, was edited and inserted into a specific template based on HTML5 and linked to Javascript libraries (Three.js) which allowed browsing on web. Subsequently, the navigation model was appropriately adapted to the purpose, so as to make the use of the network more intuitive possible, considering any type of device and using the most common browsers (Chrome, Safari, Firefox). This experimentation is a viable procedure for spreading the knowledge of a submerged archaeological site in a simple way, by web-browsing. This type of navigation models with the future development of 5G networks will find greater diffusion and application, with the possibility of including increasingly complex environments in the navigation.

show abstract

“…Machine learning has gathered particular interest as an interactive component of exhibition and art installations, e. g., Tate Modern's IK Prize 2016 winner Recognition 5 uses pattern recognition to compare art to photojournalism. For instance, Adobe's Artistic Eye 6 uses NSTs to enable children transform their self-portraits into artistic renditions in the style of a museum's exhibits, while Becattini et al (2016) combined NSTs with art explorations, allowing users to scan exhibits and transfer their style to user-de ned images.…”

Section: Exhibitions and Art Installationsmentioning

confidence: 99%

Neural style transfer

Semmo

Isenberg

Döllner

2017

Proceedings of the Symposium on Non-Photorealistic Animation and Rendering

View full text Add to dashboard Cite

HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

Imaging Novecento. A Mobile App for Automatic Recognition of Artworks and Transfer of Artistic Styles

Cited by 17 publications

References 22 publications

Neural Abstract Style Transfer for Chinese Traditional Painting

Neural Abstract Style Transfer for Chinese Traditional Painting

Accessibility to Underwater Cultural Heritage: Interactive Web Navigation of the Roman Submersed Vessel of Cala Minnola

Neural style transfer

Contact Info

Product

Resources

About