Jianwen Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jianwen Song has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Changming Sun
CSIRO Technology, Epping, Australia
5 shared publications Arcot Sowmya
3 shared publications- Arcot Sowmya
University of New South Wales
2 shared publications Kai Liu
1 shared publication- Kai Liu
Sichuan University
1 shared publication - Weichuan Zhang
School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an, China
1 shared publication
Latest Publications
- Open Access
- 5 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 331
Efficient transformer with compressed-attention for stereo image super-resolution
- 5 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 331
Open AccessEfficient transformer with compressed-attention for stereo image super-resolution
- Open Access
- 1 May 2025
- Published by Elsevier in Pattern Recognition
- Vol. 167
Efficient frequency feature aggregation transformer for image super-resolution
- 1 May 2025
- Published by Elsevier in Pattern Recognition
- Vol. 167
Open AccessEfficient frequency feature aggregation transformer for image super-resolution
- Open Access
- 24 February 2025
- Published by Elsevier in Optics and Lasers in Engineering
- Vol. 188
Universal phase retrieval transformer for single-pattern structured light three-dimensional imaging
- 24 February 2025
- Published by Elsevier in Optics and Lasers in Engineering
- Vol. 188
Open AccessUniversal phase retrieval transformer for single-pattern structured light three-dimensional imaging
- Open Access
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10094-10105
Efficient Hybrid Feature Interaction Network for Stereo Image Super-Resolution
It is very challenging to fully use cross-view information for stereo image super-resolution. Previous methods using pixel-based parallax-attention mechanisms do not consider neighborhood pixels. Also, they typically use convolutions for basic feature extraction, which may not be as effective as modern self-attention mechanisms in transformers. To address these limitations, we propose an efficient hybrid feature interaction network for stereo image super-resolution. Specifically, we propose a shifted cross-view interaction block that integrates neighborhood pixels and imposes constraints on the disparity range during cross-view interactions. In addition, we propose a hybrid feature interaction block consisting of local and global interaction branches for extracting intra-view features efficiently. In this block, we propose a design that incorporates lightweight attention connections and a partial downsampling operation to enhance spatial and channel feature interaction with high efficiency. Additionally, a dilated efficient channel attention mechanism is proposed to obtain cross-channel interactions within features. Experimental results evaluated on various metrics (PSNR, SSIM, and LPIPS) demonstrate that the proposed method achieves state-of-the-art stereo image super-resolution performance at relatively low computational cost. Moreover, the super-resolution images obtained by the proposed method achieve the smallest stereo matching errors compared to other methods. Source code will be publicly available at https://github.com/jianwensong/EHFSSR .
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10094-10105
Open AccessEfficient Hybrid Feature Interaction Network for Stereo Image Super-Resolution
It is very challenging to fully use cross-view information for stereo image super-resolution. Previous methods using pixel-based parallax-attention mechanisms do not consider neighborhood pixels. Also, they typically use convolutions for basic feature extraction, which may not be as effective as modern self-attention mechanisms in transformers. To address these limitations, we propose an efficient hybrid feature interaction network for stereo image super-resolution. Specifically, we propose a shifted cross-view interaction block that integrates neighborhood pixels and imposes constraints on the disparity range during cross-view interactions. In addition, we propose a hybrid feature interaction block consisting of local and global interaction branches for extracting intra-view features efficiently. In this block, we propose a design that incorporates lightweight attention connections and a partial downsampling operation to enhance spatial and channel feature interaction with high efficiency. Additionally, a dilated efficient channel attention mechanism is proposed to obtain cross-channel interactions within features. Experimental results evaluated on various metrics (PSNR, SSIM, and LPIPS) demonstrate that the proposed method achieves state-of-the-art stereo image super-resolution performance at relatively low computational cost. Moreover, the super-resolution images obtained by the proposed method achieve the smallest stereo matching errors compared to other methods. Source code will be publicly available at https://github.com/jianwensong/EHFSSR .
- Open Access
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 537-549
Super-Resolution Phase Retrieval Network for Single-Pattern Structured Light 3D Imaging
Structured light 3D imaging is often used for obtaining accurate 3D information via phase retrieval. Single-pattern structured light 3D imaging is much faster than multi-pattern versions. Current phase retrieval methods for single-pattern structured light 3D imaging are however not accurate enough. Besides, the projector resolution in a structured light 3D imaging system is expensive to improve due to hardware costs. To address the issues of low accuracy and low resolution of single-pattern structured light 3D imaging, this work proposes a super-resolution phase retrieval network (SRPRNet). Specifically, a phase-shifting module is proposed to extract multi-scale features with different phase shifts, and a refinement and super-resolution module is proposed to obtain refined and super-resolution phase components. After phase demodulation and unwrapping, high-resolution absolute phase is obtained. A sine shifting loss and a cosine shifting loss are also introduced to form the regularization term of the loss function. As far as can be ascertained, the proposed SRPRNet is the first network for super-resolution phase retrieval by using a single pattern, and it can also be used for standard-resolution phase retrieval. Experimental results on three datasets show that SRPRNet achieves state-of-the-art performance on 1×, 2×, and 4× super-resolution phase retrieval tasks.
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 537-549
Open AccessSuper-Resolution Phase Retrieval Network for Single-Pattern Structured Light 3D Imaging
Structured light 3D imaging is often used for obtaining accurate 3D information via phase retrieval. Single-pattern structured light 3D imaging is much faster than multi-pattern versions. Current phase retrieval methods for single-pattern structured light 3D imaging are however not accurate enough. Besides, the projector resolution in a structured light 3D imaging system is expensive to improve due to hardware costs. To address the issues of low accuracy and low resolution of single-pattern structured light 3D imaging, this work proposes a super-resolution phase retrieval network (SRPRNet). Specifically, a phase-shifting module is proposed to extract multi-scale features with different phase shifts, and a refinement and super-resolution module is proposed to obtain refined and super-resolution phase components. After phase demodulation and unwrapping, high-resolution absolute phase is obtained. A sine shifting loss and a cosine shifting loss are also introduced to form the regularization term of the loss function. As far as can be ascertained, the proposed SRPRNet is the first network for super-resolution phase retrieval by using a single pattern, and it can also be used for standard-resolution phase retrieval. Experimental results on three datasets show that SRPRNet achieves state-of-the-art performance on 1×, 2×, and 4× super-resolution phase retrieval tasks.