Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915104874823680 |
|---|---|
| author | Yang, Cuixin Dong, Rongkang Xiao, Jun Zhang, Cong Lam, Kin-Man Zhou, Fei Qiu, Guoping |
| author_facet | Yang, Cuixin Dong, Rongkang Xiao, Jun Zhang, Cong Lam, Kin-Man Zhou, Fei Qiu, Guoping |
| contents | As virtual and augmented reality applications gain popularity, omnidirectional image (ODI) super-resolution has become increasingly important. Unlike 2D plain images that are formed on a plane, ODIs are projected onto spherical surfaces. Applying established image super-resolution methods to ODIs, therefore, requires performing equirectangular projection (ERP) to map the ODIs onto a plane. ODI super-resolution needs to take into account geometric distortion resulting from ERP. However, without considering such geometric distortion of ERP images, previous deep-learning-based methods only utilize a limited range of pixels and may easily miss self-similar textures for reconstruction. In this paper, we introduce a novel Geometric Distortion Guided Transformer for Omnidirectional image Super-Resolution (GDGT-OSR). Specifically, a distortion modulated rectangle-window self-attention mechanism, integrated with deformable self-attention, is proposed to better perceive the distortion and thus involve more self-similar textures. Distortion modulation is achieved through a newly devised distortion guidance generator that produces guidance by exploiting the variability of distortion across latitudes. Furthermore, we propose a dynamic feature aggregation scheme to adaptively fuse the features from different self-attention modules. We present extensive experimental results on public datasets and show that the new GDGT-OSR outperforms methods in existing literature. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10869 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution Yang, Cuixin Dong, Rongkang Xiao, Jun Zhang, Cong Lam, Kin-Man Zhou, Fei Qiu, Guoping Image and Video Processing Computer Vision and Pattern Recognition As virtual and augmented reality applications gain popularity, omnidirectional image (ODI) super-resolution has become increasingly important. Unlike 2D plain images that are formed on a plane, ODIs are projected onto spherical surfaces. Applying established image super-resolution methods to ODIs, therefore, requires performing equirectangular projection (ERP) to map the ODIs onto a plane. ODI super-resolution needs to take into account geometric distortion resulting from ERP. However, without considering such geometric distortion of ERP images, previous deep-learning-based methods only utilize a limited range of pixels and may easily miss self-similar textures for reconstruction. In this paper, we introduce a novel Geometric Distortion Guided Transformer for Omnidirectional image Super-Resolution (GDGT-OSR). Specifically, a distortion modulated rectangle-window self-attention mechanism, integrated with deformable self-attention, is proposed to better perceive the distortion and thus involve more self-similar textures. Distortion modulation is achieved through a newly devised distortion guidance generator that produces guidance by exploiting the variability of distortion across latitudes. Furthermore, we propose a dynamic feature aggregation scheme to adaptively fuse the features from different self-attention modules. We present extensive experimental results on public datasets and show that the new GDGT-OSR outperforms methods in existing literature. |
| title | Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.10869 |