paper-with-me

홈 › Papers

SMAPGAN: Generative Adversarial Network Based Semi-Supervised Styled Map Tiles Generating Method

2020-01-21 · X. Chen, S. Chen, T. Xu, B. Yin, X. Mei, J. Peng, H. Li

Traditional online map tiles, widely used on the Internet such as Google Map and Baidu Map, are rendered from vector data. Timely updating online map tiles from vector data, of which the generating is time-consuming, is a difficult mission. It is a shortcut to generate map tiles in time from remote sensing images, which can be acquired timely without vector data. However, this mission used to be challenging or even impossible. Inspired by image-to-image translation (img2img) techniques based on generative adversarial networks (GAN), we proposed a semi-supervised Generation of styled map Tiles based on Generative Adversarial Network (SMAPGAN) model to generate styled map tiles directly from remote sensing images. In this model, we designed a semi-supervised learning strategy to pre-train SMAPGAN on rich unpaired samples and fine-tune it on limited paired samples in reality. We also designed image gradient L1 loss and image gradient structure loss to generate a styled map tile with global topological relationships and detailed edge curves of objects, which are important in cartography. Moreover, we proposed edge structural similarity index (ESSI) as a metric to evaluate the quality of topological consistency between generated map tiles and ground truths. Experimental results present that SMAPGAN outperforms state-of-the-art (SOTA) works according to mean squared error, structural similarity index, and ESSI. Also, SMAPGAN won more approval than SOTA in the human perceptual test on the visual realism of cartography. Our work shows that SMAPGAN is potentially a new paradigm to produce styled map tiles. Our implementation of the SMAPGAN is available at https://github.com/imcsq/SMAPGAN.

📄 PDF Abstract BibTeX arXiv:2001.07712

Code (2)

imcsq/S2OMGAN 공식 구현 pytorch
imcsq/SMAPGAN 공식 구현 pytorch

Tasks

Generative Adversarial NetworkImage-to-Image Translation

Methods 이 논문이 사용한 방법론

Test 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

MISS GAN: A Multi-IlluStrator Style Generative Adversarial Network for image to illustration translation

2021-08-12 · Noa Barzilay, Tal Berkovitz Shalev, Raja Giryes

Unsupervised style transfer that supports diverse input styles using only one trained generator is a challenging and interesting task in computer vision. This paper proposes a Multi-IlluStrator Style Generative Adversari…

Generative Adversarial NetworkStyle TransferTranslation

Improve Training Stability of Semi-supervised Generative Adversarial Networks with Collaborative Training

2018-01-01 · ICLR 2018 1 · Dalei Wu, Xiaohua Liu

Improved generative adversarial network (Improved GAN) is a successful method of using generative adversarial models to solve the problem of semi-supervised learning. However, it suffers from the problem of unstable trai…

General ClassificationGenerative Adversarial Network

StyleDEM: a Versatile Model for Authoring Terrains

2023-04-19 · Simon Perche, Adrien Peytavie, Bedrich Benes, Eric Galin 외

Many terrain modelling methods have been proposed for the past decades, providing efficient and often interactive authoring tools. However, they generally do not include any notion of style, which is a critical aspect fo…

Generative Adversarial NetworkmodelSuper-Resolution

Line Art Colorization of Fakemon using Generative Adversarial Neural Networks

2023-07-11 · Erick Oliveira Rodrigues, Esteban Clua, Giovani Bernardes Vitor

This work proposes a complete methodology to colorize images of Fakemon, anime-style monster-like creatures. In addition, we propose algorithms to extract the line art from colorized images as well as to extract color hi…

ColorizationLine Art Colorization

A Sea-Land Clutter Classification Framework for Over-the-Horizon-Radar Based on Weighted Loss Semi-supervised GAN

2023-05-06 · Xiaoxuan Zhang, Zengfu Wang, Kun Lu, Quan Pan 외

Deep convolutional neural network has made great achievements in sea-land clutter classification for over-the-horizon-radar (OTHR). The premise is that a large number of labeled training samples must be provided for a se…

ClassificationGenerative Adversarial Network