Newest papers

WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution

Junyuan Deng, Xinyi Wu, Zhenyao Wu, Song Wang, Yu Wang, 朱从超 · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28423 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Los métodos de superresolución (SR) basados en generaciones previas aprovechan el conocimiento implícito aprendido a partir de modelos de gran escala para mejorar las entradas efectivas de baja resolución. Sin embargo, tales previos son inherentemente estocásticos y optimizados para generaciones diversas, en conflicto con la reconstrucción determinista, de alta fidelidad requerida para SR. También está ligado al modelo base, costoso de actualizar y propenso a alucinaciones a medida que evolucionan los datos del mundo real. Para abordar estas limitaciones, introducimos WorldSR, un nuevo marco que aumenta SR con conocimiento del mundo visual explícito, alineado con entidades. WorldSR descompone automáticamente la entrada en entidades semánticas y realiza la recuperación de imágenes alineadas estructuralmente y semánticamente a medida que evolucionan. Para abordar estas limitaciones

Machine translation (Meta M2M100); the English original follows.

Abstract

Generative-prior-based super-resolution (SR) methods leverage implicit knowledge learned from large-scale models to enhance low-resolution inputs. However, such priors are inherently stochastic and optimized for diverse generation, conflicting with the deterministic, high-fidelity reconstruction required for SR. It is also tied to the base model, costly to update, and prone to hallucinations as real-world data evolves. To address these limitations, we introduce WorldSR, a novel framework that augments SR with explicit, entity-aligned visual world knowledge. WorldSR automatically decomposes the input into semantic entities and performs entity-wise retrieval of structurally and semantically aligned images from a large-scale external corpus. For efficiency and reliability, we incorporate a memory mechanism to reuse previously retrieved results and a multi-step filtering process to refine candidate references. The selected references as world knowledge are then integrated through a novel multi-reference super-resolution model, which provides fine-grained constraints for detail synthesis and structural recovery. Experiments on real-world SR benchmarks show that WorldSR consistently improves structural fidelity and visual quality, outperforming existing generative super-resolution methods. Our results suggest that entity-level grounding in external visual world knowledge provides a simple and effective complement to model-bound generative priors.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Leverage (statistics), Artificial intelligence, Reuse, Generative grammar, Fidelity

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange