CS 229 Final Report: Artistic Style Transfer for Face Portraits
نویسندگان
چکیده
The goal of our project is to learn the content and style representations of face portraits, and then to combine them to produce new pictures. The content features of a face are the features that identify a face, such as the outline shape. The stylistic features are the artistic characteristics of a certain portrait or painting, such as brush strokes, or background color. We forward-pass a content image, and several style images through a CNN to extract the desired content and style features. Then we initialize a white noise image, and perform gradient descent on its pixels until it matches the desired style and content features.
منابع مشابه
Deep Learning Based Identity Verification in Renaissance Portraits
The identity of subjects in many portraits has been a matter of debate by art historians that relied on subjective analysis of facial features. Developing automated face verification technique has thus garnered interest to provide a quantitative way to reinforce the decision arrived by the art historians. However, most existing works often fail to resolve ambiguities concerning the identity of ...
متن کاملArtistic Rendering of Portraits
This chapter presents an overview of the latest artistic portrait rendering techniques. Artistic rendering or portraits can be viewed as an image generating process controlled by two factors. The first one is the face fidelity, namely, a rendered portrait image should preserve a certain amount of the original face’s information. The second factor is the artistic style, for example, sketch, pain...
متن کاملArtistic Rendering of Human Portraits Paying Attention to Facial Features
Artistic painting of human portraits are more challenging than landscapes or flowers. Challenges are eye and nose areas where we need to avoid alterations from their natural appearance. Shades or darkness around eyes, or shininess at the nose tip may negatively impact the rendering result if not properly dealt with. The proposed computerized method attempts to be adaptive to those sensitive are...
متن کاملIdentity-preserving Face Recovery from Portraits
Recovering the latent photorealistic faces from their artistic portraits aids human perception and facial analysis. However, recovering photorealistic faces from stylized portraits while preserving identity is challenging because the fine details of real faces can be distorted or lost in stylized images. In this paper, we present a new Identity-preserving Face Recovery from Portraits (IFRP) met...
متن کاملRepresentation and Aesthetics of the Human Face in Portraiture
How do representations of the face in portraits relate to the natural face, and how does the aesthetics of portraits relate to the aesthetics of faces in photographs? Here we investigate these questions with regard to the frontal face. Frontal faces are of particular interest because they are by far the most commonly studied type of face image in psychology, yet frontal portraits have been litt...
متن کامل