跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 18 天前AI 評分35

UniRestorer++:以多粒度退化建模實現可擴展的通用影像復原

UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling

AI 導讀

UniRestorer++提出以多粒度退化建模和自適應路由為基礎的可擴展通用影像復原框架,透過逐步細化退化羣組及引入專家模型,兼顧專門化與穩健性。研究團隊建立涵蓋 50 種退化類別的 CDD-50 基準;實驗顯示,在評估的模型規模範圍內,PSNR 趨勢約呈對數線性,且在分佈外及真實世界數據上的擴展增益高於 vanilla MoE scaling。

正文

Published on Nov 4

Authors:

,

,

,

,

,

Abstract

UniRestorer++ scales universal image restoration via multi-granularity degradation modeling and adaptive routing, achieving stronger scaling and generalization across diverse degradations.

Universal image restoration aims to handle diverse degradations within a single model, but a reliable scaling strategy remains underexplored. Increasing backbone depth and width can lead to performance saturation, while degradation-aware specialization depends on accurate degradation estimation and is vulnerable to errors on out-of-distribution and real-world inputs. We propose UniRestorer++, a scalable framework based on multi-granularity degradation modeling. It progressively refines degradation groups and introduces group-specific experts, coupling capacity growth with specialization. Degradation-estimation-based routing selects a root-to-leaf path, while granularity-estimation-based routing chooses a level along that path to balance specialization and robustness. Spatially dense degradation representation maps further enable region-aware routing for spatially non-uniform corruptions. We develop CDD-50, a benchmark covering 50 degradation categories from single to penta-degradation. Experiments show approximately log-linear PSNR trends over the evaluated model-size range and stronger scaling gains on out-of-distribution and real-world data than vanilla MoE scaling. UniRestorer++ achieves state-of-the-art performance across benchmarks and demonstrates zero-shot generalization and few-shot transfer on real-world images. Code: https://github.com/mrluin/UniRestorer_plusplus

View arXiv page View PDF GitHub 2 Add to collection

Get this paper in your agent:

hf papers read 2611.06042

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.06042 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.06042 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.06042 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co