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∘×360∘ 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×} inference acceleration. Our code and models will be released upon acceptance.
@article{arxiv.2412.09646,
title = {RealOSR: Latent Guidance Boosts Diffusion-based Real-world Omnidirectional Image Super-Resolutions},
author = {Xuhan Sheng and Runyi Li and Bin Chen and Weiqi Li and Xu Jiang and Jian Zhang},
journal= {arXiv preprint arXiv:2412.09646},
year = {2026}
}