Proceedings Article10.1109/ICIP.2009.5413801
Image retargeting using importance diffusion
Sunghyun Cho,Hanul Choi,Yasuyuki Matsushita,Seungyong Lee +3 more
- 07 Nov 2009
- pp 973-976
TL;DR: Experimental result demonstrates that importance diffusion successfully improves the retargeting results of row/ column removal and seam carving, and provides control over the trade-off between uniform and non-uniform sampling for the row/column removal and seams carving methods.
read more
Abstract: This paper presents a simple and effective image retargeting method that preserves visually important parts while reducing unwanted distortions of an image. Our approach is based on a novel importance diffusion scheme, which propagates importance of removed pixels to their neighbors for preserving visual contexts and avoiding over-shrinkage of unimportant parts. Importance diffusion enables even a simple row/column removal method, which removes the least important rows/columns repeatedly, to produce visually pleasant results. It also provides control over the trade-off between uniform and non-uniform sampling for the row/column removal and seam carving methods. Experimental result demonstrates that importance diffusion successfully improves the retargeting results of row/column removal and seam carving.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A survey of image retargeting techniques
TL;DR: This work review and categorize algorithms for contentaware image retargeting, i.e., resizing an image while taking its content into consideration to preserve important regions and minimize distortions, as it requires preserving the relevant information while maintaining an aesthetically pleasing image for the user.
159
Spatiotemporal Saliency Detection Using Textural Contrast and Its Applications
Won Jun Kim,Changick Kim +1 more
TL;DR: The proposed scheme outperforms other previously developed methods in detecting salient regions of the static and dynamic scenes and can be easily extended to various applications, such as image retargeting, object segmentation, and video surveillance.
79
Stretchability-aware block scaling for image retargeting
TL;DR: This paper proposes an efficient approach to retarget images based on stretchability-aware block scaling based on gradient, saliency and color features that achieves an overall better retargeting performance compared to the state-of-the-art image retargeted approaches.
35
Learning to resize image
TL;DR: The proposed method for image resizing can generate much less seams cutting through the ROI compared with previous efforts toward the same goal and the desirable regions can be preserved in the target image and the structural consistency of the input image is naturally maintained.
29
A Texture-Aware Salient Edge Model for Image Retargeting
Won Jun Kim,Changick Kim +1 more
TL;DR: This letter introduces a novel IIM by exploiting the higher order statistics of the diffusion space for image retargeting and defines it as texture-aware salient edge (TASE) map, which has been extensively tested and experimental results show that the proposed scheme is effective for imageretargeting compared to other various state-of-the-art methods.
21
References
Seam carving for content-aware image resizing
Shai Avidan,Ariel Shamir +1 more
- 29 Jul 2007
TL;DR: In this article, seam carving is used for content-aware image resizing for both reduction and expansion, where an optimal 8-connected path of pixels on a single image from top to bottom, or left to right, where optimality is defined by an image energy function.
Seam carving for content-aware image resizing
AvidanShai,ShamirAriel +1 more
TL;DR: In this article, a simple image operator called seam carving is presented that supports content-aware resizing of images by considering the image content as well as the geometric constraints of the image.
1K
Improved seam carving for video retargeting
Michael Rubinstein,Ariel Shamir,Shai Avidan +2 more
- 01 Aug 2008
TL;DR: This work replaces the dynamic programming method of seam carving with graph cuts that are suitable for 3D volumes and presents a novel energy criterion that improves the visual quality of the retargeted images and videos.
851
Summarizing visual data using bidirectional similarity
Denis Simakov,Yaron Caspi,E. Shechtman,Michal Irani +3 more
- 23 Jun 2008
TL;DR: This work proposes a principled approach to summarization of visual data based on optimization of a well-defined similarity measure and shows that the same approach can be used to address a variety of other problems, including automatic cropping, completion and synthesis ofVisual data, image collage, object removal, photo reshuffling and more.
Optimized scale-and-stretch for image resizing
Yu-Shuen Wang,Chiew-Lan Tai,Olga Sorkine,Tong-Yee Lee +3 more
- 01 Dec 2008
TL;DR: The technique allows diverting the distortion due to resizing to image regions with homogeneous content, such that the impact on perceptually important features is minimized, and distributes the distortion in all spatial directions.
721
Related Papers (5)
Shai Avidan,Ariel Shamir +1 more
- 29 Jul 2007
Michael Rubinstein,Ariel Shamir,Shai Avidan +2 more
- 01 Aug 2008
Michael Rubinstein,Ariel Shamir,Shai Avidan +2 more
- 27 Jul 2009
Yu-Shuen Wang,Chiew-Lan Tai,Olga Sorkine,Tong-Yee Lee +3 more
- 01 Dec 2008