Xiang Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiang Yao has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Jingtao Wang
State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China
1 shared publication - Yun Pan
State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China
1 shared publication
Latest Publications
- Open Access
- 28 April 2024
- Published by MDPI AG in Information
- Vol. 15 (5) , 248
An Omnidirectional Image Super-Resolution Method Based on Enhanced SwinIR
For the significant distortion problem caused by the special projection method of equi-rectangular projection (ERP) images, this paper proposes an omnidirectional image super-resolution algorithm model based on position information transformation, taking SwinIR as the base. By introducing a space position transformation module that supports deformable convolution, the image preprocessing process is optimized to reduce the distortion effects in the polar regions of the ERP image. Meanwhile, by introducing deformable convolution in the deep feature extraction process, the model’s adaptability to local deformations of images is enhanced. Experimental results on publicly available datasets have shown that our method outperforms SwinIR, with an average improvement of over 0.2 dB in WS-PSNR and over 0.030 in WS-SSIM for ×4 pixel upscaling.
- 28 April 2024
- Published by MDPI AG in Information
- Vol. 15 (5) , 248
Open AccessAn Omnidirectional Image Super-Resolution Method Based on Enhanced SwinIR
For the significant distortion problem caused by the special projection method of equi-rectangular projection (ERP) images, this paper proposes an omnidirectional image super-resolution algorithm model based on position information transformation, taking SwinIR as the base. By introducing a space position transformation module that supports deformable convolution, the image preprocessing process is optimized to reduce the distortion effects in the polar regions of the ERP image. Meanwhile, by introducing deformable convolution in the deep feature extraction process, the model’s adaptability to local deformations of images is enhanced. Experimental results on publicly available datasets have shown that our method outperforms SwinIR, with an average improvement of over 0.2 dB in WS-PSNR and over 0.030 in WS-SSIM for ×4 pixel upscaling.