OPDN: Omnidirectional Position-aware Deformable Network for Omnidirectional Image Super-Resolution
This work addresses the specific issue of image quality in immersive technologies like AR/VR, representing an incremental improvement in a domain-specific area.
The paper tackles the problem of low angular resolution in 360° omnidirectional images, which are crucial for AR/VR applications, by proposing a two-stage framework that achieves superior performance and wins the NTIRE 2023 challenge for this task.
360° omnidirectional images have gained research attention due to their immersive and interactive experience, particularly in AR/VR applications. However, they suffer from lower angular resolution due to being captured by fisheye lenses with the same sensor size for capturing planar images. To solve the above issues, we propose a two-stage framework for 360° omnidirectional image superresolution. The first stage employs two branches: model A, which incorporates omnidirectional position-aware deformable blocks (OPDB) and Fourier upsampling, and model B, which adds a spatial frequency fusion module (SFF) to model A. Model A aims to enhance the feature extraction ability of 360° image positional information, while Model B further focuses on the high-frequency information of 360° images. The second stage performs same-resolution enhancement based on the structure of model A with a pixel unshuffle operation. In addition, we collected data from YouTube to improve the fitting ability of the transformer, and created pseudo low-resolution images using a degradation network. Our proposed method achieves superior performance and wins the NTIRE 2023 challenge of 360° omnidirectional image super-resolution.