Depth-Induced Intra-to-Inter Transformer network for stereoscopic image retargeting
With the advancement of three-dimension visual applications, stereoscopic image editing technologies have attracted widespread popularity in both industry and entertainment. In this paper, we focus on the fundamental stereoscopic image content editing problem, i.e. stereoscopic image retargeting, wh...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-04-01
|
| Series: | Engineering Science and Technology, an International Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215098625000849 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850055669352235008 |
|---|---|
| author | Xiaoting Fan Long Sun Zhong Zhang |
| author_facet | Xiaoting Fan Long Sun Zhong Zhang |
| author_sort | Xiaoting Fan |
| collection | DOAJ |
| description | With the advancement of three-dimension visual applications, stereoscopic image editing technologies have attracted widespread popularity in both industry and entertainment. In this paper, we focus on the fundamental stereoscopic image content editing problem, i.e. stereoscopic image retargeting, which aims to transform stereoscopic images to specific resolution with prescribed aspect ratios adaptively. Due to the additional binocular information present between the left and right views in stereoscopic images, the CNN-based stereoscopic image retargeting methods have some obvious limitations in capturing long-range dependencies. To address these issues, we present a depth-induced intra-to-inter Transformer network (DITrans-Net) for stereoscopic image retargeting, which learns the long-range dependencies information between intra-view and inter-view by an intra-to-inter feature extraction module and aggregates the depth information of left view and right view by a depth-induced feature integration module. Specifically, an intra-to-inter feature extraction module exploits intra-to-inter Transformer blocks for long-range dependencies information extraction firstly. Furthermore, a depth-induced feature integration module employs disparity attention learning mechanism to learn stereo correspondence and enhance disparity varying consistency. Finally, a hybrid loss function is applied to improve the stereoscopic image retargeting quality. Extensive experiments demonstrate that the proposed DITrans-Net achieves significant improvements and outperforms state-of-the-art methods both quantitatively and qualitatively on the various benchmark datasets. |
| format | Article |
| id | doaj-art-abf39ebf2c0e4c46b2d19bc6d7f072b5 |
| institution | DOAJ |
| issn | 2215-0986 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Engineering Science and Technology, an International Journal |
| spelling | doaj-art-abf39ebf2c0e4c46b2d19bc6d7f072b52025-08-20T02:51:53ZengElsevierEngineering Science and Technology, an International Journal2215-09862025-04-016410202910.1016/j.jestch.2025.102029Depth-Induced Intra-to-Inter Transformer network for stereoscopic image retargetingXiaoting Fan0Long Sun1Zhong Zhang2Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin 300387, PR ChinaSchool of Information and Engineering, Tianjin University of Commerce, Tianjin 300134, PR ChinaTianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin 300387, PR China; Corresponding author.With the advancement of three-dimension visual applications, stereoscopic image editing technologies have attracted widespread popularity in both industry and entertainment. In this paper, we focus on the fundamental stereoscopic image content editing problem, i.e. stereoscopic image retargeting, which aims to transform stereoscopic images to specific resolution with prescribed aspect ratios adaptively. Due to the additional binocular information present between the left and right views in stereoscopic images, the CNN-based stereoscopic image retargeting methods have some obvious limitations in capturing long-range dependencies. To address these issues, we present a depth-induced intra-to-inter Transformer network (DITrans-Net) for stereoscopic image retargeting, which learns the long-range dependencies information between intra-view and inter-view by an intra-to-inter feature extraction module and aggregates the depth information of left view and right view by a depth-induced feature integration module. Specifically, an intra-to-inter feature extraction module exploits intra-to-inter Transformer blocks for long-range dependencies information extraction firstly. Furthermore, a depth-induced feature integration module employs disparity attention learning mechanism to learn stereo correspondence and enhance disparity varying consistency. Finally, a hybrid loss function is applied to improve the stereoscopic image retargeting quality. Extensive experiments demonstrate that the proposed DITrans-Net achieves significant improvements and outperforms state-of-the-art methods both quantitatively and qualitatively on the various benchmark datasets.http://www.sciencedirect.com/science/article/pii/S2215098625000849Stereoscopic imageImage retargetingLong-range dependencies informationIntra-to-inter feature extractionDepth-induced feature integration |
| spellingShingle | Xiaoting Fan Long Sun Zhong Zhang Depth-Induced Intra-to-Inter Transformer network for stereoscopic image retargeting Engineering Science and Technology, an International Journal Stereoscopic image Image retargeting Long-range dependencies information Intra-to-inter feature extraction Depth-induced feature integration |
| title | Depth-Induced Intra-to-Inter Transformer network for stereoscopic image retargeting |
| title_full | Depth-Induced Intra-to-Inter Transformer network for stereoscopic image retargeting |
| title_fullStr | Depth-Induced Intra-to-Inter Transformer network for stereoscopic image retargeting |
| title_full_unstemmed | Depth-Induced Intra-to-Inter Transformer network for stereoscopic image retargeting |
| title_short | Depth-Induced Intra-to-Inter Transformer network for stereoscopic image retargeting |
| title_sort | depth induced intra to inter transformer network for stereoscopic image retargeting |
| topic | Stereoscopic image Image retargeting Long-range dependencies information Intra-to-inter feature extraction Depth-induced feature integration |
| url | http://www.sciencedirect.com/science/article/pii/S2215098625000849 |
| work_keys_str_mv | AT xiaotingfan depthinducedintratointertransformernetworkforstereoscopicimageretargeting AT longsun depthinducedintratointertransformernetworkforstereoscopicimageretargeting AT zhongzhang depthinducedintratointertransformernetworkforstereoscopicimageretargeting |