EUVIMEDEUVIMED entdecken
Crossref

Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution

Xiao He, Zhijun Tu, Kun Cheng, Mingrui Zhu, Jie Hu, Nannan Wang, Xinbo Gao

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4681-4689

DOI: 10.1609/aaai.v40i6.42469 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xiao He und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The demonstrated success of sparsely-gated Mixture-of-Experts (MoE) architectures, exemplified by models such as DeepSeek and Grok, has motivated researchers to investigate their adaptation to diverse domains. In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models through Low-Rank Adaptation (LoRA) module to reconstruct high-resolution (HR) images. However, these dense Real-ISR models are limited in their ability to adaptively capture the heterogeneous characteristics of complex real-world degraded samples or enable knowledge sharing between inputs under equivalent computational budgets. To address this, we investigate the integration of sparse MoE into Real-ISR and propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution. We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert. This design enables flexible knowledge recombination while isolating fixed-position ranks as shared experts to preserve common-sense features and minimize routing redundancy. Furthermore, we develop a degradation estimation module leveraging CLIP embeddings and predefined positive-negative text pairs to compute relative degradation scores, dynamically guiding expert activation. To better accommodate varying sample complexities, we incorporate zero-expert slots and propose a degradation-aware load-balancing loss, which dynamically adjusts the number of active experts based on degradation severity, ensuring optimal computational resource allocation. Comprehensive experiments validate our framework's effectiveness and state-of-the-art performance.

Zitieren

APA

He, X., Tu, Z., Cheng, K., Zhu, M., Hu, J., Wang, N., & Gao, X. (2026). Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4681-4689. https://doi.org/10.1609/aaai.v40i6.42469

Vancouver

He X, Tu Z, Cheng K, Zhu M, Hu J, Wang N, et al. Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4681-4689. doi:10.1609/aaai.v40i6.42469

BibTeX
@article{He2026,
  author = {He, Xiao and Tu, Zhijun and Cheng, Kun and Zhu, Mingrui and Hu, Jie and Wang, Nannan and Gao, Xinbo},
  title = {Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {6},
  pages = {4681--4689},
  doi = {10.1609/aaai.v40i6.42469}
}
Kostenlos starten →