An Advert Creation System for 3D Product Placements

被引：1

作者：

Bacher, Ivan ^{[1
]}

Javidnia, Hossein ^{[1
]}

Dev, Soumyabrata ^{[1
,2
]}

Agrahari, Rahul ^{[1
]}

Hossari, Murhaf ^{[1
]}

Nicholson, Matthew ^{[1
]}

Conran, Clare ^{[1
]}

Tang, Jian ^{[3
]}

Song, Peng ^{[3
]}

Corrigan, David ^{[3
]}

Pitie, Francois ^{[1
,4
]}

机构：

[1] Trinity Coll Dublin, Adapt SFI Res Ctr, Dublin, Ireland

[2] Univ Coll Dublin, Sch Comp Sci, Dublin, Ireland

[3] Huawei Ireland Res Ctr, Dublin, Ireland

[4] Trinity Coll Dublin, Dept Elect & Elect Engn, Dublin, Ireland

来源：

MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: APPLIED DATA SCIENCE TRACK, ECML PKDD 2020, PT IV | 2021年 / 12460卷

关键词：

Advertisement; Augmented reality; Deep learning;

D O I：

10.1007/978-3-030-67667-4_14

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Over the past decade, the evolution of video-sharing platforms has attracted a significant amount of investments on contextual advertising. The common contextual advertising platforms utilize the information provided by users to integrate 2D visual ads into videos. The existing platforms face many technical challenges such as ad integration with respect to occluding objects and 3D ad placement. This paper presents a Video Advertisement Placement & Integration (Adverts) framework, which is capable of perceiving the 3D geometry of the scene and camera motion to blend 3D virtual objects in videos and create the illusion of reality. The proposed framework contains several modules such as monocular depth estimation, object segmentation, background-foreground separation, alpha matting and camera tracking. Our experiments conducted using Adverts framework indicates the significant potential of this system in contextual ad integration, and pushing the limits of advertising industry using mixed reality technologies.

引用

页码：224 / 239

页数：16

共 38 条

[1]

Agarwal S, 2010, LECT NOTES COMPUT SC, V6312, P29, DOI 10.1007/978-3-642-15552-9_3

[2] Semantic Soft Segmentation [J].

Aksoy, Yagiz ;

Oh, Tae-Hyun ;

Paris, Sylvain ;

Pollefeys, Marc ;

Matusik, Wojciech .

ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (04)

[3] A database and evaluation methodology for optical flow [J].

Baker, Simon ;

Scharstein, Daniel ;

Lewis, J. P. ;

Roth, Stefan ;

Black, Michael J. ;

Szeliski, Richard .

2007 IEEE 11TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1-6, 2007, :588-595

[4]

Basha T, 2012, PROC CVPR IEEE, P1426, DOI 10.1109/CVPR.2012.6247830

[5] Semiparallel deep neural network hybrid architecture: first application on depth from monocular camera [J].

Bazrafkan, Shabab ;

Javidnia, Hossein ;

Lemley, Joseph ;

Corcoran, Peter .

JOURNAL OF ELECTRONIC IMAGING, 2018, 27 (04)

[6]

Caelles S., 2018, The 2018 DAVIS Challenge on Video Object Segmentation

[7] Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning [J].

Chen, Yuhua ;

Pont-Tuset, Jordi ;

Montes, Alberto ;

Van Gool, Luc .

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :1189-1198

[8]

Chuang YY, 2001, PROC CVPR IEEE, P264

[9] Advertisement detection and replacement using acoustic and visual repetition [J].

Covell, Michele ;

Baluja, Shumeet ;

Fink, Michael .

2006 IEEE WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING, 2006, :461-+

[10] Projective Multiview Structure and Motion from Element-Wise Factorization [J].

Dai, Yuchao ;

Li, Hongdong ;

He, Mingyi .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (09) :2238-2251

← 1 2 3 4 →