305 Hits in 4.2 sec

Stereoscopic image retargeting based on 3D saliency detection

Junle Wang, Yuming Fang, Manish Narwaria, Weisi Lin, Patrick Le Callet
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In this paper, we propose a novel stereoscopic image retargeting algorithm based on 3D visual saliency detection.  ...  A geometrically consistent seam carving technique is adopted for retargeting stereo image pair.  ...  Therefore, it is not a trivial work to develop new visual attention model for 3D content and integrate the 3D visual attention model into the stereoscopic image retargeting framework.  ... 
doi:10.1109/icassp.2014.6853680 dblp:conf/icassp/WangFNLC14 fatcat:vbhsmernojfqpfpf2e2bki4nsa

Real-time adaptive content retargeting for live multi-view capture and light field display

Vamsi Kiran Adhikarla, Fabio Marton, Tibor Balogh, Enrico Gobbetti
2015 The Visual Computer  
We propose an efficient on-thefly content-aware real-time depth retargeting algorithm for live 3D light field video to increase the quality of visual perception on a cluster-driven multiprojector light  ...  Keywords On-the-fly depth retargeting · GPU · Multiprojector light field display · Visually enhanced live 3D Video · Multi-view capture and display  ...  Retargeting model Given a 3D scene our aim is to produce a retargeted scene which meets the given depth constraints of a light field display. Light field display.  ... 
doi:10.1007/s00371-015-1127-6 fatcat:uebjmwbksbecpfd2qgwhtzkrsq

A Survey on Content Aware Image Resizing Methods

2020 KSII Transactions on Internet and Information Systems  
This paper presents a survey on various image retargeting methods, comparison of image retargeting results based on performance, and also exposes the main challenges in image retargeting such as content  ...  With the advancement in the field of image processing, images are being processed using various image processing algorithms.  ...  [67] proposed a method through which an energy map can be obtained by combining the traditional L−1 norm of the gradient with depth-aware saliency (3D saliency).  ... 
doi:10.3837/tiis.2020.07.015 fatcat:qm2yfnvqzrf5ld6vgt46z2mg3a

3D Thumbnails for Mobile Media Browser Interface with Autostereoscopic Displays [chapter]

R. Bertan Gundogdu, Yeliz Yigit, Tolga Capin
2010 Lecture Notes in Computer Science  
In this paper, we focus on the problem of how to visualize and browse 3D videos and 3D images in a media browser application, running on a 3D-enabled mobile device with an autostereoscopic display.  ...  We propose a 3D thumbnail representation format and an algorithm for automatic 3D thumbnail generation from a 3D video + depth content.  ...  Acknowledgments This work is supported by FP7 ICT All 3D Imaging Phone (3DPHONE) project. The depth images shown in this work are courtesy of Fraunhofer Heinrich Hertz Institute.  ... 
doi:10.1007/978-3-642-11301-7_61 fatcat:c2xtgsgulnfjhdrsp7fke4naly

Hybrid Distortion Aggregated Visual Comfort Assessment for Stereoscopic Image Retargeting [article]

Ya Zhou, Zhibo Chen, Weiping Li
2018 arXiv   pre-print
Visual comfort is a quite important factor in 3D media service.  ...  We validate the effectiveness of HDA-VCA on published Stereoscopic Image Retargeting Database (SIRD) and two stereoscopic image databases IEEE-SA and NBU 3D-VCA.  ...  A full-reference quality assessment model for image retargeting considering natural scene statistics (NSS) modeling and bi-directional saliency similarity is introduced in [16] .  ... 
arXiv:1811.12687v1 fatcat:643ydzywcbbfdjgrauaqfirjjy

Multi-operator retargeting based on perceptual structural similarity

Yuming Fang, Weisi Lin, Zhou Wang, Zhijun Fang, Long Xu, Yong Yang
2014 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)  
Experimental results on a public image retargeting database show the promising performance of the proposed multi-operator retargeting algorithm.  ...  Since the sizes of original and retargeted images are different, SIFT flow is used for dense correspondence between the original and retargeted images for similarity evaluation.  ...  In this study, we our previous model in compressed domain [13] , while the topdown saliency map S t is estimated by a face detector [22] .  ... 
doi:10.1109/chinasip.2014.6889276 dblp:conf/chinasip/FangLWFXY14 fatcat:pyx6ldhlufc6honmurubgmuoqy

Image Modification Based on Spatial Frequency Components for Visual Attention Retargeting

Hironori TAKIMOTO, Syuhei HITOMI, Hitoshi YAMAUCHI, Mitsuyoshi KISHIHARA, Kensuke OKUBO
2017 IEICE transactions on information and systems  
In this paper, we propose a novel image modification method for guiding user attention to specific regions of interest by using a novel saliency map model based on spatial frequency components.  ...  Using gaze measurements, we show that the proposed saliency map matches well with the distribution of actual human attention.  ...  Acknowledgments This research was partially supported by a Grant-in-Aid for Scientific Research (C) from the Japan Society for the Promotion of Science (grant no. 15K00282).  ... 
doi:10.1587/transinf.2016edp7413 fatcat:6ovsldtahfdzxnahakclo7zmhm

Cycle-IR: Deep Cyclic Image Retargeting [article]

Weimin Tan, Bo Yan, Chumin Lin, Xuejing Niu
2019 arXiv   pre-print
In this paper, we propose a novel deep cyclic image retargeting approach, called Cycle-IR, to firstly implement image retargeting with a single deep model, without relying on any explicit user annotations  ...  Deep learning techniques may help to address this issue, but the challenging problem is that we need to build a large-scale image retargeting dataset for the training of deep retargeting models.  ...  DEEP CYCLIC IMAGE RETARGETING Our goal is to develop a deep image-retargeting model that can directly generate high-quality target images when users provide input images with arbitrary sizes and desired  ... 
arXiv:1905.03556v1 fatcat:emzuu6wydfhlxcwnzz7b3q5elq

Content aware video manipulation

Moshe Guttmann, Lior Wolf, Danny Cohen-Or
2011 Computer Vision and Image Understanding  
The visual performance of the proposed algorithm is demonstrated on a variety of video sequences, and compared to the state-of-the-art in image retargeting.  ...  One main motivation of CAVM is "video retargeting", a process that visually alters an existing video while considering the relative importance of its various regions.  ...  Saliency We aim at modeling the visual attention by mapping each pixel with a saliency measure, where value is considered an unattractive pixel and 1 is an important pixel.  ... 
doi:10.1016/j.cviu.2011.05.010 fatcat:hh6h53errbaahiuppclty5vn3y

Human Attention Modelization and Data Reduction [chapter]

Matei Mancas, Dominique De, Nicolas Riche, Xavier Siebert
2012 Video Compression  
The eye movements are in this approach directly an output from the model and do not have to be inferred from a saliency map.  ...  For this reason, the following sections in this first part of the chapter will also mainly deal with saliency methods, but a review of visibility methods will be provided in the end.  ...  Automatic image retargeting with fisheye-view warping Liu & Gleicher (2005) uses an "importance map" that combines salience and object information to find automatically, with a greedy algorithm, a minimal  ... 
doi:10.5772/34942 fatcat:esq57asj2vf27gzfir4ycx36im

Warping-based video retargeting for stereoscopic video

Stephan Kopf, Benjamin Guthier, Christopher Hipp, Johannes Kiess, Wolfgang Effelsberg
2014 2014 IEEE International Conference on Image Processing (ICIP)  
In this paper, a novel warping-based retargeting approach for stereoscopic video is proposed.  ...  The first step of the approach focuses on content-aware image resizing and considers image saliency, motion saliency, and depth saliency.  ...  Quads with a high saliency contain important image content and should thus be scaled uniformly.  ... 
doi:10.1109/icip.2014.7025586 dblp:conf/icip/KopfGHKE14 fatcat:2opz7dzu3fhotpsuwdnvv3kyha

Seamlet carving for shape-aware image resizing

Xiao Lin, Bin Sheng, LiZhuang Ma, Yang Shen, ZhiHua Chen
2012 Science China Information Sciences  
Unlike the traditional seam-carving methods, our approach can construct a seamlet to handle the discontinuous pixels and further achieve an optimized image resizing results with shape-preservation.  ...  Seamlet carving for shape-aware image resizing.  ...  They used graph cuts to suit for 3D volumes by removing 2D seam manifolds from 3D space-time volumes. They used a minimal cut in the graph to get a seam with the seam being monotonic and connected.  ... 
doi:10.1007/s11432-012-4565-z fatcat:sg5e6th5tnfsfnzmjszqxwjbwi

Efficient random saliency map detection

ZhiYong Huang, FaZhi He, XianTao Cai, ZhengQin Zou, Jing Liu, MingMing Liang, Xiao Chen
2011 Science China Information Sciences  
Efficient random saliency map detection SCIENTIA SINICA Informationis 41, 863 (2011); A computational coding model for saliency detection in primary visual cortex  ...  The concepts from image retargeting have also been transferred to content-aware shape resizing and focus+context visualization of 3D models [17] .  ...  Almost all the image retargeting methods can be adapted to resize videos by addressing two problems: augmenting image importance models with motion information and resizing individual frames in a temporally  ... 
doi:10.1007/s11432-011-4263-2 fatcat:27qeu5s6dnfdta5ai3ps6xcqqa

Efficient Scale-Space Spatiotemporal Saliency Tracking for Distortion-Free Video Retargeting [chapter]

Gang Hua, Cha Zhang, Zicheng Liu, Zhengyou Zhang, Ying Shan
2010 Lecture Notes in Computer Science  
In this paper, we propose a novel approach to distortion-free video retargeting by scale-space spatiotemporal saliency tracking.  ...  Video retargeting aims at transforming an existing video in order to display it appropriately on a target device, often in a lower resolution, such as a mobile phone.  ...  We assume in this section such a saliency map is available (see Sec. 4 for our computation model for the spatiotemporal saliency map).  ... 
doi:10.1007/978-3-642-12304-7_18 fatcat:iscpdovgfvao7cohsqup5gxzye

Video retargeting

Feng Liu, Michael Gleicher
2006 Proceedings of the 14th annual ACM international conference on Multimedia - MULTIMEDIA '06  
Video retargeting crops each frame and scales it to fit the target display.  ...  An optimization process minimizes information loss by balancing the loss of detail due to scaling with the loss of content and composition due to cropping.  ...  The methods from still images, salience and object identification, are extended with motion features in Section 3.1. Second, we consider more general types of loss due to retargeting.  ... 
doi:10.1145/1180639.1180702 dblp:conf/mm/LiuG06 fatcat:7igu3tpezjeshgn5dbcx7ugi44
« Previous Showing results 1 — 15 out of 305 results