Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution

TL;DR

This paper introduces GDGT-OSR, a novel transformer-based method that effectively accounts for geometric distortion in omnidirectional image super-resolution, significantly improving reconstruction quality by leveraging distortion-aware self-attention mechanisms.

Contribution

The paper proposes a distortion-guided transformer with a novel self-attention mechanism and dynamic feature fusion specifically designed for omnidirectional image super-resolution.

Findings

Outperforms existing methods on public datasets.

Effectively models geometric distortion for better texture reconstruction.

Enhances self-similar texture perception in ODIs.

Abstract

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.