Shadow matting and compositing

Author:

Chuang Yung-Yu1,Goldman Dan B1,Curless Brian1,Salesin David H.1,Szeliski Richard2

Affiliation:

1. University of Washington

2. Microsoft Research

Abstract

In this paper, we describe a method for extracting shadows from one natural scene and inserting them into another. We develop physically-based shadow matting and compositing equations and use these to pull a shadow matte from a source scene in which the shadow is cast onto an arbitrary planar background. We then acquire the photometric and geometric properties of the target scene by sweeping oriented linear shadows (cast by a straight object) across it. From these shadow scans, we can construct a shadow displacement map without requiring camera or light source calibration. This map can then be used to deform the original shadow matte. We demonstrate our approach for both indoor scenes with controlled lighting and for outdoor scenes using natural lighting.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design

Reference21 articles.

1. Image inpainting

2. Environment matting extensions: Towards higher accuracy and real-time capture;CHUANG Y.-Y.;Proceedings of ACM SIGGRAPH,2000

3. Video matting of complex scenes

Cited by 61 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. DMAED: Dynamic Matte Aware Encoder-Decoder for Shadow Removal;Proceedings of the 2024 3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy;2024-03

2. A review of advancements in deep learning-based shadow detection and removal in image and video analysis;International Journal of Intelligent Engineering Informatics;2024

3. Shadow Harmonization for Realistic Compositing;SIGGRAPH Asia 2023 Conference Papers;2023-12-10

4. A dynamic alignment and illumination‐aware convolution for shadow removal;IET Image Processing;2023-12-03

5. UnShadowNet: Illumination Critic Guided Contrastive Learning for Shadow Removal;IEEE Access;2023

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