Optimizing content-preserving projections for wide-angle images

Author:

Carroll Robert1,Agrawal Maneesh1,Agarwala Aseem2

Affiliation:

1. University of California, Berkeley

2. Adobe Systems, Inc.

Abstract

Any projection of a 3D scene into a wide-angle image unavoidably results in distortion. Current projection methods either bend straight lines in the scene, or locally distort the shapes of scene objects. We present a method that minimizes this distortion by adapting the projection to content in the scene, such as salient scene regions and lines, in order to preserve their shape. Our optimization technique computes a spatially-varying projection that respects user-specified constraints while minimizing a set of energy terms that measure wide-angle image distortion. We demonstrate the effectiveness of our approach by showing results on a variety of wide-angle photographs, as well as comparisons to standard projections.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design

Reference32 articles.

1. Photographing long scenes with multi-viewpoint panoramas

2. Seam carving for content-aware image resizing

3. Bradski G. and Kaehler A. 2008. Learning OpenCV: Computer Vision with the OpenCV Library. O'Reilly Cambridge MA. Bradski G. and Kaehler A. 2008. Learning OpenCV: Computer Vision with the OpenCV Library . O'Reilly Cambridge MA.

4. An invitation to discuss computer depiction

Cited by 73 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. A Perceptual Measure for Deep Single Image Camera and Lens Calibration;IEEE Transactions on Pattern Analysis and Machine Intelligence;2023-09-01

2. A New Method for WFOV Camera Distortion Correction;2023 WRC Symposium on Advanced Robotics and Automation (WRC SARA);2023-08-19

3. Wide-Angle Rectification via Content-Aware Conformal Mapping;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06

4. SIR: Self-Supervised Image Rectification via Seeing the Same Scene From Multiple Different Lenses;IEEE Transactions on Image Processing;2023

5. Utilization of Vision Transformer for Classification and Ranking of Video Distortions;Artificial Neural Networks in Pattern Recognition;2022-11-11

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