Supplemental Document for Deep Photo Style Transfer
نویسندگان
چکیده
This document contains: links to two user studies (section 1), comparison against Wu et al. [6] (section 2), results with only semantic segmentation or photorealism regularization (section 3), merging classes for DilatedNet [1] Segmentation (section 4), a solution for handling noisy (section 5) or high-resolution (section 6) input, an extension for CNNMRF in photographic transfer (section 7), and some ideas we came up with, but ultimately did not work well, before reaching the matting Laplacian solution (section 8).
منابع مشابه
Face Sketch Synthesis with Style Transfer using Pyramid Column Feature
In this paper, we propose a novel framework based on deep neural networks for face sketch synthesis from a photo. Imitating the process of how artists draw sketches, our framework synthesizes face sketches in a cascaded manner. A content image is first generated that outlines the shape of the face and the key facial features. Textures and shadings are then added to enrich the details of the ske...
متن کاملContent Aware Neural Style Transfer
In the emerging inter-disciplinary field of art and image processing, algorithms have been developed to assist the analysis of art work. In most applications, especially brush stroke analysis, high resolution digital images of paintings are required to capture subtle patterns and details in the high frequency range of the spectrum. Algorithms have been developed to learn styles of painters from...
متن کاملDeep Semantics-Aware Photo Adjustment
Automatic photo adjustment is to mimic the photo retouching style of professional photographers and automatically adjust photos to the learned style. There have been many attempts to model the tone and the color adjustment globally with low-level color statistics. Also, spatially varying photo adjustment methods have been studied by exploiting high-level features and semantic label maps. Those ...
متن کاملTowards Deep Style Transfer: A Content-Aware Perspective
Recently, it has been shown that one can invert a deep convolutional neural network originally trained for classification tasks to transfer image style. There is, however, a dearth of research on content-aware style transfer. In this paper, we generalize the original neural algorithm [1] for style transfer from two perspectives: where to transfer and what to transfer. To specify where to transf...
متن کاملNetizen-Style Commenting on Fashion Photos: Dataset and Diversity Measures
Recently, deep neural network models have achieved promising results in image captioning task. Yet, “vanilla” sentences, only describing shallow appearances (e.g., types, colors), generated by current works are not satisfied netizen style resulting in lacking engagements, contexts, and user intentions. To tackle this problem, we propose Netizen Style Commenting (NSC), to automatically generate ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017