<p>Image super-resolution (SR) plays a critical role in enhancing visual quality and improving the performance of downstream vision tasks. However, existing SR methods are predominantly trained and evaluated on standardized datasets, which limits their generalization and robustness in complex real-world scenarios. As a representative application domain, movie scenes exhibit high structural complexity and visual diversity, often containing special effects, filters, and other non-natural elements that pose additional challenges for SR models. Traditional prior-based methods lack strong constraints and often involve random sampling. In fact, a vast amount of high-quality imagery has become available on the Web, offering rich external priors that can potentially enhance SR performance. Motivated by this, we propose a novel reference-based SR framework for movie scenes, termed Multi-Scale Mixture-of-Experts ControlNet (MMoEControl). Our approach first retrieves semantically or structurally similar high-quality images from web-scale data based on features extracted from the low-resolution (LR) input, forming a reference image set. Then we design a Multi-Scale Mixture-of-Experts (MMoE) framework built upon an improved ControlNet architecture, which injects the reference information into a frozen pre-trained diffusion model to guide the generation of HR outputs. The MMoE effectively mitigates the randomness of prior-based sampling and makes efficient use of the beneficial information contained in the reference image set. Experimental results demonstrate that our approach consistently outperforms existing methods in various real-world movie scenes, highlighting its strong generalization and practical value.</p>