3D Wikipedia

Author:

Russell Bryan C.1,Martin-Brualla Ricardo2,Butler Daniel J.2,Seitz Steven M.2,Zettlemoyer Luke2

Affiliation:

1. Intel Labs

2. University of Washington

Abstract

We introduce an approach for analyzing Wikipedia and other text, together with online photos, to produce annotated 3D models of famous tourist sites. The approach is completely automated, and leverages online text and photo co-occurrences via Google Image Search. It enables a number of new interactions, which we demonstrate in a new 3D visualization tool. Text can be selected to move the camera to the corresponding objects, 3D bounding boxes provide anchors back to the text describing them, and the overall narrative of the text provides a temporal guide for automatically flying through the scene to visualize the world as you read about it. We show compelling results on several major tourist sites.

Funder

Pervasive Computing

Intel Corporation

Division of Information and Intelligent Systems

Google

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design

Reference37 articles.

1. Building Rome in a day

2. Berlitz International I. 2003. Berlitz Rome Pocket Guide. Berlitz Pocket Guides Series. Berlitz International Incorporated. Berlitz International I. 2003. Berlitz Rome Pocket Guide . Berlitz Pocket Guides Series. Berlitz International Incorporated.

Cited by 18 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. HaLo‐NeRF: Learning Geometry‐Guided Semantics for Exploring Unconstrained Photo Collections;Computer Graphics Forum;2024-04-15

2. Viki LibraRy;Proceedings of the 34th ACM Conference on Hypertext and Social Media;2023-09-04

3. Analyzing suicide life stories on Wikipedia with Highway_star and other textual visualization tools;SN Social Sciences;2021-10-29

4. Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision;2021 IEEE/CVF International Conference on Computer Vision (ICCV);2021-10

5. Harvesting Visual Objects from Internet Images via Deep-Learning-Based Objectness Assessment;ACM Transactions on Multimedia Computing, Communications, and Applications;2019-08-31

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