Abstract:

Traditional Video Super-Resolution （VSR） methods are ineffective in solving geometric distortion problems caused by equirectangular projection when processing panoramic videos， and have deficiencies in inter-frame alignment and feature fusion， which results in poor reconstruction quality. To further improve the super-resolution reconstruction quality of panoramic videos， a panoramic video super-resolution network combining spherical alignment and adaptive geometric correction， named 360GeoVSR， was proposed. In the network， accurate alignment and efficient fusion of inter-frame features were achieved through a Spherical Alignment Module （SAM） and a Geometric Fusion Block （GFB）. In SAM， spatial transformation and deformable convolution were combined to address global and local geometric distortions. In GFB， feature alignment was corrected dynamically using an embedded Adaptive Geometric Correction （AGC） submodule， and multi-frame information was fused to capture complex inter-frame relationships. The results of subjective and objective comparison experiments on the extended ODV360Extended panoramic video dataset show that 360GeoVSR outperforms five representative super-resolution methods， including BasicVSR++ and VRT （Video Restoration Transformer）， in both objective metrics and subjective visual effects， verifying its effectiveness.

Key words: panoramic video, super-resolution, geometric correction, spherical alignment, deep learning

摘要：

现有的传统视频超分辨率（VSR）方法在处理全景视频时难以有效解决等距矩形投影带来的几何畸变问题，且在帧间对齐和特征融合方面存在不足，这些会导致重建效果不佳。为了进一步提升全景视频的超分辨率重建质量，提出一种结合球面对齐与自适应几何校正的全景视频超分辨率网络——360GeoVSR。该网络通过球面对齐模块（SAM）和几何融合块（GFB）实现帧间特征的精确对齐与高效融合。SAM结合空间变换和可变形卷积处理全局与局部几何畸变；GFB通过嵌入的自适应几何校正（AGC）子模块动态校正特征对齐，并融合多帧信息以捕捉复杂的帧间关系。在扩展的ODV360Extended全景视频数据集上的主客观对比实验结果表明，360GeoVSR在客观指标和主观视觉效果上均优于BasicVSR++和VRT（Video Restoration Transformer）等5种代表性超分辨率方法，验证了它的有效性。

关键词: 全景视频, 超分辨率, 几何校正, 球面对齐, 深度学习