Loop-Mamba: A Loop Mamba with Degradation-Aware and Shared Memory for Old Photo Restoration 文章

ArXiv CS.CV2026-08-04PAPERen作者: Runci Bai, Yucheng Xin, Pu Wang, Yongcong Wang, Chen Wu, Dianjie Lu, Guijuan Zhang, Pengwen Dai, Guangwei Gao, Siyuan Yao, Zhuoran Zheng

详细信息

来源站点
ArXiv CS.CV
作者
Runci Bai, Yucheng Xin, Pu Wang, Yongcong Wang, Chen Wu, Dianjie Lu, Guijuan Zhang, Pengwen Dai, Guangwei Gao, Siyuan Yao, Zhuoran Zheng
文章类型
PAPER
语言
en
发布日期
2026-08-04

摘要

arXiv:2608.02346v1 Announce Type: new Abstract: Old photographs often suffer from multiple coupled degradations, including scratches, cracks, fading, blur, noise, and missing regions, severely degrading both visual quality and semantic content. We propose Loop-Mamba, a lightweight loop-based state-space framework that formulates old photo restoration as progressive state evolution, where a persis- tent restoration state is continuously propagated and refined through iterative computation. Specifically, we introduce a Semantic-Guided Degradation Estimator (SGDE) to explicitly model heterogeneous degradations by jointly predicting local degradation maps and global degradation scores, providing degradation-aware guidance for state evolution.

相关事件

暂无数据

相关公司查看全部 (5)

A
Advanced Photon SourceRESEARCH_INSTITUTE
A
AMBANONPROFIT

相关人物

暂无数据