科技前沿

基于图像的虚拟光影技术研究热点

  • 吴洪宇 ,
  • 金鑫
展开
  • 1. 虚拟现实技术与系统国家重点实验室, 北京航空航天大学计算机学院, 北京 100191;
    2. 北京电子科技学院网络空间安全系, 北京 100070
吴洪宇,助理研究员,研究方向为虚拟现实、计算机图形学、计算机图像处理,电子信箱:whyvrlab@buaa.edu.cn

收稿日期: 2019-02-01

  修回日期: 2019-05-31

  网络出版日期: 2020-05-11

基金资助

国家自然科学基金项目(61902014,61402021);国家重点研发计划项目(2018YFC0831003)

A review of hot topics in image-based virtual lighting

  • WU Hongyu ,
  • JIN Xin
Expand
  • 1. State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing 100191, China;
    2. Department of Cyber Security, Beijing Electronic Science and Technology Institute, Beijing 100070, China

Received date: 2019-02-01

  Revised date: 2019-05-31

  Online published: 2020-05-11

摘要

基于图像的虚拟光影技术是直接改变图像场景中物体的光影效果或者估计场景光照,在光影维度对图像进行增强,并保留图像物体的视觉特征。从光影效果迁移、虚实光照融合两个方面盘点了虚拟光影技术的重要研究成果,展望了该领域关键技术的发展趋势。

本文引用格式

吴洪宇 , 金鑫 . 基于图像的虚拟光影技术研究热点[J]. 科技导报, 2020 , 38(6) : 141 -152 . DOI: 10.3981/j.issn.1000-7857.2020.06.020

Abstract

The image-based virtual relighting (IBVR) is to directly modify the lighting effect of an object in the image or to estimate the lighting condition of the image. Unlike the traditional image processing technology, the images are processed in the domain of lighting, retaining the visual characteristics of an object. This paper reviews the important research advances of the IBVR in 2018, as well as its trend of development.

参考文献

[1] Wikipedia. VES[EB/OL].[2019-07-21]. https://en.wikipedia.org/wiki/Image-based_modeling_and_rendering.
[2] Paul Debevec. VES[EB/OL].[2019-07-21]. http://www.pauldebevec.com/.
[3] Chabert C F, Einarsson P, Jones A, et al. Relighting human locomotion with flowed reflectance fields[C]//ACM SIGGRAPH 2006 Sketches. New York:ACM, 2006:76.
[4] Chen J, Su G, He J, et al. Face image relighting using locally constrained global optimization[C]//European Conference on Computer Vision. Springer, Berlin, Heidelberg, 2010:44-57.
[5] Fuchs M, Blanz V, Lensch H, et al. Adaptive sampling of reflectance fields[J]. ACM Transactions on Graphics, 2007, 26(2):10.
[6] Ren P, Wang J, Gong M, et al. Global illumination with radiance regression functions[J]. ACM Transactions on Graphics, 2013, 32(4):130.
[7] Meka A, Haene C, Pandey R, et al. Deep reflectance fields-high-quality facial reflectance field inference from color gradient illumination[J]. ACM Transactions on Graphics, 2019, 38(4):77.
[8] Ren P, Dong Y, Lin S, et al. Image based relighting using neural networks[J]. ACM Transactions on Graphics, 2015, 34(4):111.
[9] Ng R, Ramamoorthi R, Hanrahan P. All-frequency shadows using non-linear wavelet lighting approximation[J]. ACM Transactions on Graphics. 2003, 22(3):376-381.
[10] Xu Z, Sunkavalli K, Hadap S, et al. Deep image-based relighting from optimal sparse samples[J]. ACM Transactions on Graphics, 2018, 37(4):126.
[11] Barrow H, Tenenbaum J. Recovering intrinsic scene characteristics[J]. Computer Vision System, 1978, 2(3-26):2.
[12] Zhang R, Tsai P S, Cryer J E, et al. Shape-from-shading:A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(8):690-706.
[13] Chai M, Luo L, Sunkavalli K, et al. High-quality hair modeling from a single portrait photo[J]. ACM Transactions on Graphics, 2015, 34(6):204.
[14] Kanamori Y, Endo Y. Relighting humans:Occlusionaware inverse rendering for full body human images[J]. ACM Transactions on Graphics, 2018, 37(6):1-270.
[15] Sun T, Barron J T, Tsai Y T, et al. Single image portrait relighting[J]. ACM Transactions on Graphics, 2019, 38(4):79.
[16] Wu J H, Saito S. Interactive relighting in single low-dynamic range images[J]. ACM Transactions on Graphics, 2017, 36(2):18.
[17] Philip J, Gharbi M, Zhou T, et al. Multi-view relighting using a geometry-aware network[J]. ACM Transactions on Graphics, 2019, 38(4):78.
[18] Shashua A, Riklin-Raviv T. The quotient image:Classbased re-rendering and recognition with varying illuminations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(2):129-139.
[19] Peers P, Tamura N, Matusik W, et al. Post-production facial performance relighting using reflectance transfer[J]. ACM Transactions on Graphics, 2007, 26(3):52.
[20] Li Q, Yin W, Deng Z. Image-based face illumination transferring using logarithmic total variation models[J]. The Visual Computer, 2010, 26(1):41.
[21] Shu Z, Hadap S, Shechtman E, et al. Portrait lighting transfer using a mass transport approach[J]. ACM Transactions on Graphics, 2018, 37(1):2.
[22] Wikipedia. VES[EB/OL].[2019-07-21]. https://en.wikipedia.org/wiki/Augmented_reality.
[23] Yi R, Zhu C, Tan P, et al. Faces as lighting probes via unsupervised deep highlight extraction[C]//European Conference on Computer Vision. Springer, Berlin, Heidelberg, 2018:317-333.
[24] Hold-Geoffroy Y, Sunkavalli K, Hadap S, et al. Deep outdoor illumination estimation[C]//IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Washington, DC, 2017:2373-2382.
[25] Gardner M A, Sunkavalli K, Yumer E, et al. Learning to predict indoor illumination from a single image[J]. ACM Transactions on Graphics, 2017, 36(6):176.
[26] SUN360. VES[EB/OL].[2019-07-21]. http://people.csail.mit.edu/jxiao/SUN360/index_high.html.
[27] Barreira J, Bessa M, Barbosa L, et al. A context-aware method for authentically simulating outdoors shadows for mobile augmented reality[J]. IEEE transactions on visualization and computer graphics, 2018, 24(3):1223-1231.
[28] Karsch K, Hedau V, Forsyth D, et al. Rendering synthetic objects into legacy photographs[J]. ACM Transactions on Graphics, 2011, 30(6):157.
[29] Karsch K, Sunkavalli K, Hadap S, et al. Automatic scene inference for 3d object compositing[J]. ACM Transactions on Graphics, 2014, 33(3):32.
[30] Karsch K, Liu C, Kang S B. Depth transfer:Depth extraction from video using non-parametric sampling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(11):2144-2158.
[31] Liao Z, Karsch K, Forsyth D. An approximate shading model for object relighting[C]//IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Washington, DC, 2015:5307-5314.
文章导航

/