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

Korean

생성-prior-based super-resolution (SR) 방법은 대규모 모델에서 배운 암시적인 지식을 활용하여 효율적인 낮은 해상도 입력을 향상시킵니다. 그러나, 그러한 priors는 본질적으로 스토카스틱하고 다양한 세대에 최적화되며, SR에 필요한 결정적이고 높은 신뢰성의 재구성과 충돌합니다. 그것은 또한 기본 모델에 묶여 있으며 업데이트하는 데 비용이 많이 들며 실제 데이터가 진화함에 따라 환각에 취약합니다. 이러한 제한을 해결하기 위해 우리는 WorldSR, 명시적 인, 엔티티 타이밍 된 시각적 세계 지식으로 SR를 증가시키는 새로운 프레임 워크를 도입합니다. WorldSR는 자동으로 세멘틱 엔티에 입력을 분해하고 구조적으로 및 세멘티 타이밍 된

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