Jump map-based interactive texture synthesis

Author:

Zelinka Steve1,Garland Michael1

Affiliation:

1. University of Illinois at Urbana-Champaign, Urbana, IL

Abstract

We present techniques for accelerated texture synthesis from example images. The key idea of our approach is to divide the task into two phases: analysis, and synthesis. During the analysis phase, which is performed once per sample texture, we generate a <i>jump map</i>. Using the jump map, the synthesis phase is capable of synthesizing texture similar to the analyzed example at interactive rates. We describe two such synthesis phase algorithms: one for creating images, and one for directly texturing manifold surfaces. We produce texture images at rates comparable to the fastest alternative algorithms, and produce textured surfaces an order of magnitude faster than current alternative approaches. We further develop a new, faster patch-based algorithm for image synthesis, which improves the quality of our results on ordered textures. We show how controls used for specifying texture synthesis on surfaces may be used on images as well, allowing interesting new image-based effects, and highlight modelling applications enabled by the speed of our approach.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design

Cited by 20 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Fast and high-quality video inpainting by efficiently patch searching and synthesizing;2023 4th International Conference on Computer Vision, Image and Deep Learning (CVIDL);2023-05-12

2. Layered leaf texturing using structure-guided model;Graphical Models;2019-05

3. PatchSwapper: A novel real-time single-image editing technique by region-swapping;Computers & Graphics;2018-06

4. Methods to Choose the ‘Best-Fit’ Patch in Patch-Based Texture Synthesis Algorithm;Advances in Intelligent Systems and Computing;2017-11-25

5. Metric-Driven RoSy Field Design and Remeshing;IEEE Transactions on Visualization and Computer Graphics;2010-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3