An Advert Creation System for 3D Product Placements

  title={An Advert Creation System for 3D Product Placements},
  author={Ivan Bacher and Hossein Javidnia and Soumyabrata Dev and Rahul Agrahari and Murhaf Hossari and Matthew Nicholson and Clare Conran and Jian Tang and Peng Song and David Corrigan and Franccois Piti'e},
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… Expand
DeepReal-A Deep Learning Based 3D Advert Integration System
This research project aims to provide an AI enhanced productivity tool for media generation to video editors and producers. The goal is to improve productivity among producers and artists in terms ofExpand
Stereo Matching Based on Visual Sensitive Information
Aiming at the limitation of traditional stereo matching algorithms regarding the cost window, a cost aggregation algorithm based on the dynamic window is proposed, and the disparity image is optimized by using left and right consistency detection to further reduce the error matching rate. Expand


ADNet: A Deep Network for Detecting Adverts
This approach is the first of its kind that automatically detects the presence of adverts in a video frame, and achieves state-of-the-art results on a public dataset. Expand
The ALOS Dataset for Advert Localization in Outdoor Scenes
This paper proposes and releases the first large-scale dataset of advertisement billboards, captured in outdoor scenes, and benchmark several state-of-the-art semantic segmentation algorithms on this proposed dataset. Expand
An Advert Creation System for Next-Gen Publicity
A system that can effectively integrate a new advertisement into a video sequence, using state-of-the-art techniques from deep learning and computational photogrammetry, for effective detection of existing adverts, and seamless integration of new adverts into video sequences. Expand
Localizing Adverts in Outdoor Scenes
This paper proposes DeepAds – a deep neural network, based on the simple encoder-decoder architecture, that can accurately localize the position of an advert in a video frame, and achieves the best performance. Expand
The CASE Dataset of Candidate Spaces for Advert Implantation
This paper attempts to assist the video editors to generate augmented video content, by proposing candidate spaces in video frames, and proposes and releases a large-scale dataset of outdoor scenes, along with manually annotated maps for candidate spaces. Expand
Automatic Understanding of Image and Video Advertisements
The novel problem of automatic advertisement understanding is proposed, and a dataset of 64,832 image ads and 3,477 video ads is created to enable research on this problem. Expand
Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning
The proposed method supports different kinds of user input such as segmentation mask in the first frame (semi-supervised scenario), or a sparse set of clicked points (interactive scenario), and reaches comparable quality to competing methods with much less interaction. Expand
The 2018 DAVIS Challenge on Video Object Segmentation
This edition of the DAVIS Challenge on Video Object Segmentation adds an interactive segmentation teaser track, where the participants will interact with a web service simulating the input of a human that provides scribbles to iteratively improve the result. Expand
Semantic soft segmentation
This work introduces semantic soft segments, a set of layers that correspond to semantically meaningful regions in an image with accurate soft transitions between different objects, and proposes a graph structure that embeds texture and color features from the image as well as higher-level semantic information generated by a neural network. Expand
Advertisement Detection and Replacement using Acoustic and Visual Repetition
A method for detecting and precisely segmenting repeated sections of broadcast streams and allowing advertisements to be removed and replaced with new ads in redistributed television material is proposed. Expand