Cross-Consistent Deep Unfolding Network for Adaptive All-In-One Video Restoration

TL;DR

This paper introduces a novel deep unfolding network that adaptively restores videos degraded by various adverse weather conditions using a single model, reducing complexity and improving performance.

Contribution

The paper presents the first all-in-one video restoration model capable of adaptively removing diverse degradations with a new iterative optimization framework and degradation estimation.

Findings

Achieves state-of-the-art performance in all-in-one video restoration

Effectively estimates degradation features for adaptive processing

Utilizes inter-frame fusion to leverage distant temporal information

Abstract

Existing Video Restoration (VR) methods always necessitate the individual deployment of models for each adverse weather to remove diverse adverse weather degradations, lacking the capability for adaptive processing of degradations. Such limitation amplifies the complexity and deployment costs in practical applications. To overcome this deficiency, in this paper, we propose a Cross-consistent Deep Unfolding Network (CDUN) for All-In-One VR, which enables the employment of a single model to remove diverse degradations for the first time. Specifically, the proposed CDUN accomplishes a novel iterative optimization framework, capable of restoring frames corrupted by corresponding degradations according to the degradation features given in advance. To empower the framework for eliminating diverse degradations, we devise a Sequence-wise Adaptive Degradation Estimator (SADE) to estimate degradation features for the input corrupted video. By orchestrating these two cascading procedures, CDUN achieves adaptive processing for diverse degradation. In addition, we introduce a window-based inter-frame fusion strategy to utilize information from more adjacent frames. This strategy involves the progressive stacking of temporal windows in multiple iterations, effectively enlarging the temporal receptive field and enabling each frame's restoration to leverage information from distant frames. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance in All-In-One VR.