MSTGAR: Multioperator-Based Stereoscopic Thumbnail Generation With Arbitrary Resolution

Chai, Xiongli; Shao, Feng; Jiang, Qiuping; Ho, Yo‐Sung

doi:10.1109/tmm.2019.2939707

Cited by 10 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides depth preservation, Shao et al [22] further consider visual comfort for stereo image retargeting. Chai et al [23] propose a hybrid method which combines warping and cropping to generate thumbnail for stereo images.…”

Section: Related Workmentioning

confidence: 99%

Shape-Preserving Stereo Object Remapping via Object-Consistent Grid Warping

Lin

Zheng

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Viewing various stereo images under different viewing conditions has escalated the need for effective object-level remapping techniques. In this paper, we propose a new object spatial mapping scheme, which adjusts the depth and size of the selected object to match user preference and viewing conditions. Existing warping-based methods often distort the shape of important objects or cannot faithfully adjust the depth/size of the selected object due to improper warping such as local rotations. In this paper, by explicitly reducing the transformation freedom degree of warping, we propose an optimization model based on axis-aligned warping for object spatial remapping. The proposed axis-aligned warping based optimization model can simultaneously adjust the depths and sizes of selected objects to their target values without introducing severe shape distortions. Moreover, we propose object consistency constraints to ensure the size/shape of parts inside a selected object to be consistently adjusted. Such constraints improve the size/shape adjustment performance while remaining robust to some extent to incomplete object extraction. Experimental results demonstrate that the proposed method achieves high flexibility and effectiveness in adjusting the size and depth of objects compared with existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Shape-Preserving Stereo Object Remapping via Object-Consistent Grid Warping

Lin

Zheng

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Failing to achieve this can easily incur viewing discomfort which can cause the image to lose its 3D property. An even better method is proposed by [31] which introduces a multi operator based novel thumbnail generation strategy with two innovations. The ҥrst is a warping technique to redirect a stereopair into six-scale resolutions with distinct contexts and then the second innovation focuses on cropping the six scale images via a cropping network, this then further optimise those images into something of a targeted scale resolution by the use of visual representational energy of the desired images.…”

mentioning

confidence: 99%

Thumbnail Generation for User Defined Aspect Ratios

Verma,

Singh,

et al. 2023

Preprint

View full text Add to dashboard Cite

A thumbnail is a scaled-down version of an image that provides a visual summary with low resolution. Thumbnails are commonly used in digital media like Photo galleries and video-sharing websites. Through this research, a comparison has been presented between three thumbnail generation techniques and for what scenarios they are suitable. The first two methods are predefined methods provided by Microsoft Azure Services and do not provide satisfactory results. The third method discussed in this paper uses a traditional deep learning approach by modifying the layers of the VGG-16 model and performing regression on a dataset of 1000 images to give bounding box coordinates of the most important area of the image as the output and a validation accuracy of 47.99 percent. A competitive analysis with respect to the results is shown in the below sections.

show abstract

An Efficient Hybrid Sequence of Retargeting Operators to Minimize Structural Deformities in Image

Garg,

Singh

et al. 2024

Springer Proceedings in Physics

View full text Add to dashboard Cite

MSTGAR: Multioperator-Based Stereoscopic Thumbnail Generation With Arbitrary Resolution

Cited by 10 publications

References 46 publications

Shape-Preserving Stereo Object Remapping via Object-Consistent Grid Warping

Shape-Preserving Stereo Object Remapping via Object-Consistent Grid Warping

Thumbnail Generation for User Defined Aspect Ratios

An Efficient Hybrid Sequence of Retargeting Operators to Minimize Structural Deformities in Image

Contact Info

Product

Resources

About