Scene recognition systems are generally based on features that represent the image semantics by modeling the content depicted in a given image. In this paper we propose a framework for scene recognition that goes beyond the mere visual content analysis by exploiting a new cue for categorization: the image composition, namely its photographic style and layout. We extract information about the im...

This note presents an extension to the neural artistic style transfer algorithm [2]. The original algorithm transforms an image to have the style of another given image. For example, a photograph can be transformed to have the style of a famous painting. Here we address a potential shortcoming of the original method: the algorithm transfers the colors of the original painting, which can alter t...

We have developed an efficient virtual dissection tool to create generic 3D models for anatomical atlases without the need for artistic drawings. Our custom-developed tool can be used to extract 3D models from 2D medical image stacks, cut the models and align the sub-models. Corresponding 2D medical image portions of the sub-models can then be registered and averaged. In the end, a generic mode...

Virtual museums are commonly intended as collections of digital resources containing artistic and cultural images. They can be an appealing enhancement of a museum or can also be accessed by remote hosts (Web Museum). The realization of a virtual museum is based on the collection of large, high resolution and accurate images, that can be managed using an Image Server. This paper propose a new I...

Realistic image manipulation is challenging because it requires modifying the image appearance in a user-controlled way, while preserving the realism of the result. Unless the user has considerable artistic skill, it is easy to “fall off” the manifold of natural images while editing. In this paper, we propose to learn the natural image manifold directly from data using a generative adversarial ...

bstract. We integrate stylized rendering with an efficient multiesolution image representation, enabling a user to control how ompression affects the aesthetic appearance of an image. We dopt a point-based rendering approach to progressive image transission and compression. We use a novel, adaptive farthest point ampling algorithm to represent the image at progressive levels of etail, balancing...

There has been fascinating work on creating artistic transformations of images by Gatys et al. This was revolutionary in how we can in some sense alter the “style” of an image while generally preserving its “content”. In this work, we present a method for creating new sounds using a similar approach. For demonstration, we investigate two different tasks, resulting in bandwidth expansion/compres...

The major contribution of this paper is the use and define energy functions that study the visual features, such as image gradients, to preserve the important content of an image. Classical methods of resizing or cropping images have limitations in the sense that they distort or cut important regions of an image. By applying higher energy around pixels containing faces and lower energy for back...

This paper describes an environment for editing and performing interactive media art/entertainment. The design background is to provide artistic/entertainment pieces, in which multiple people can participate without special sensory equipment. This paper introduces a gesture input function using color tags in the image and some matching functions to be used for writing a piece. This paper shows ...

Artistic style transfer has long been an interesting topic in computer vision research. Recently several methods for style transfer based on convolutional neural networks have been proposed. This project aims at understanding and implementing some of the existing methods. More specifically we succeed in implementing the optimization based neural algorithm as well as the real-time style transfer...