RealOSR: Latent Guidance Boosts Diffusion-based Real-world Omnidirectional Image Super-Resolutions

TL;DR

RealOSR introduces a diffusion-based approach with latent guidance for real-world omnidirectional image super-resolution, achieving high quality and over 200 times faster inference than previous methods.

Contribution

The paper proposes RealOSR, a novel diffusion framework with a lightweight latent guidance module, enabling efficient one-step denoising for real-world ODISR.

Findings

Significant visual quality improvements over existing methods.

Over 200x faster inference compared to recent diffusion-based approaches.

Effective pixel-latent interactions via LaGAR module.

Abstract

Omnidirectional image super-resolution (ODISR) aims to upscale low-resolution (LR) omnidirectional images (ODIs) to high-resolution (HR), catering to the growing demand for detailed visual content across a $ 180^{\circ}\times360^{\circ}$ viewport. Existing ODISR methods are limited by simplified degradation assumptions (e.g., bicubic downsampling), failing to model and exploit the real-world degradation information. Recent latent-based diffusion approaches using condition guidance suffer from slow inference due to their hundreds of updating steps and frequent use of VAE. To tackle these challenges, we propose \textbf{RealOSR}, a diffusion-based framework tailored for real-world ODISR, featuring efficient latent-based condition guidance within a one-step denoising paradigm. Central to efficient latent-based condition guidance is the proposed \textbf{Latent Gradient Alignment Routing (LaGAR)}, a lightweight module that enables effective pixel-latent space interactions and simulates gradient descent directly in the latent space, thereby leveraging the semantic richness and multi-scale features captured by the denoising UNet. Compared to the recent diffusion-based ODISR method, OmniSSR, RealOSR achieves significant improvements in visual quality and over \textbf{200$\times$} inference acceleration. Our code and models will be released upon acceptance.