计算机视觉
计算机科学
图像分辨率
全向天线
人工智能
投影(关系代数)
空间频率
融合
光学
算法
物理
电信
哲学
天线(收音机)
语言学
作者
Dezhi Li,Yonglin Chen,Xingbo Dong,Tiong-Sik Ng,Zhe Jin,Shengyuan Wang,Wen Sha
标识
DOI:10.1117/1.jei.34.2.023008
摘要
Omnidirectional images (ODIs) possess unique equirectangular projection geometric properties that pose challenges for traditional super-resolution methods. Existing ODI super-resolution (ODISR) models often struggle to effectively capture both spatial and frequency domain information, limiting their performance. We introduce a lightweight model that fuses information from both domains to enhance ODISR. A dual-domain attention mechanism tailored for ODISR is proposed, incorporating a reparameterized pixel attention module and a frequency-domain attention module. This approach achieves a balance between efficiency and reconstruction quality, reducing both time and space complexity. Experiments demonstrate that our model outperforms state-of-the-art lightweight ODISR models while maintaining competitive performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI