D$^{2}$R$^{2}$OSR: Degradation-Disentangled Representation for Real-World Omnidirectional Image Super-Resolution

2026-06-28

AI Summary

This work addresses the challenge that existing real-world super-resolution methods struggle to effectively handle the complex degradations and geometric distortions introduced during fisheye imaging and equirectangular projection (ERP) of panoramic images. To this end, the authors propose a degradation-decoupled representation framework that, for the first time, integrates projection priors and characteristics of human immersive visual perception into degradation modeling. The approach employs a dual-branch architecture to jointly leverage both ERP and perspective projection representations (PPR) centered around the viewer’s gaze, and introduces a degradation-specific module (DSM) to explicitly decouple geometric distortion from authentic image degradation. The method achieves state-of-the-art performance across multiple metrics, producing high-fidelity, visually superior super-resolved panoramic images while maintaining low computational overhead, making it suitable for resource-constrained scenarios.

Abstract

With the growing demand for immersive visual experiences, high-quality omnidirectional images (ODIs) have become increasingly important. However, limitations in imaging devices and transmission bandwidth often lead to low-resolution ODIs, hindering the rendering of fine-grained 360° details, especially in the presence of real-world degradations and geometric distortions. Existing real-world super-resolution (Real-SR) methods are inadequate for ODIs, as their degradation models fail to account for the complex imaging pipeline involving fisheye capture and Equirectangular Projection (ERP), introducing severe aliasing and projection-specific distortions. To address these challenges, we propose D$^{2}$R$^{2}$OSR, a Degradation-Disentangled Representation framework for Real-world Omnidirectional image Super-Resolution. D$^{2}$R$^{2}$OSR explicitly models degradations arising from both fisheye imaging and ERP projection, guided by two key insights: (1) projection priors play a critical role in shaping real-world degradations, and (2) human perception in immersive environments is inherently viewpoint-centric. Accordingly, we introduce a Perspective Projection Representation (PPR) operating alongside the ERP branch to capture viewpoint-aware features, together with a Degradation-Specific Module (DSM) that jointly models ERP-induced geometric distortions and PPR-specific real-world degradations. Extensive experiments demonstrate that D$^{2}$R$^{2}$OSR achieves state-of-the-art performance and produces visually compelling, high-fidelity omnidirectional Real-SR results while maintaining favorable computational efficiency for low-resource deployment.

Problem

• Omnidirectional Image Super-Resolution
• Real-World Degradation
• Equirectangular Projection
• Geometric Distortion
• Fisheye Imaging

Innovation

• Omnidirectional Image Super-Resolution
• Degradation Disentanglement
• Equirectangular Projection
• Perspective Projection Representation
• Real-World Super-Resolution