arXiv cs.AI· Junyuan Deng, Xinyi Wu, Zhenyao Wu, Song Wang, Yu Wang, Congchao Zhu·· 12 小时前AI 评分29
WorldSR：用世界知识搜索实现有依据的图像超分辨率
WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution
AI 导读
WorldSR 框架通过将输入分解为语义实体、从大规模外部语料库按实体检索结构语义对齐的参考图像，为超分辨率提供显式世界知识约束。该框架引入记忆机制复用已检索结果，并用多步过滤筛选候选参考，再经多参考超分辨率模型融合。在真实世界 SR benchmark 上，WorldSR 的结构保真度与视觉质量稳定优于现有生成式超分辨率方法，论文已被 NeurIPS 2026 接收。
正文 · 原文
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.
| Comments: | Accepted at NeurIPS 2026. Project Page: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28423 [cs.CV] |
| (or arXiv:2610.28423v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28423 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junyuan Deng [view email]
[v1]
Tue, 20 Oct 2026 15:54:25 UTC (29,046 KB)
来源：arXiv cs.AI · arxiv.org