Coarse to Fine: Image Restoration Boosted by Multi-Scale Low-Rank Tensor Completion

TL;DR

This paper introduces a coarse-to-fine image restoration method using multi-scale low-rank tensor completion, effectively balancing detail preservation and complex object reconstruction.

Contribution

It proposes a novel coarse-to-fine strategy that adaptively searches local ranks, overcoming the limitations of global low-rank assumptions in tensor completion.

Findings

Outperforms existing tensor completion methods in image restoration tasks.

Effectively balances detail preservation and complex object reconstruction.

Demonstrates superior performance through extensive experiments.

Abstract

Existing low-rank tensor completion (LRTC) approaches aim at restoring a partially observed tensor by imposing a global low-rank constraint on the underlying completed tensor. However, such a global rank assumption suffers the trade-off between restoring the originally details-lacking parts and neglecting the potentially complex objects, making the completion performance unsatisfactory on both sides. To address this problem, we propose a novel and practical strategy for image restoration that restores the partially observed tensor in a coarse-to-fine (C2F) manner, which gets rid of such trade-off by searching proper local ranks for both low- and high-rank parts. Extensive experiments are conducted to demonstrate the superiority of the proposed C2F scheme. The codes are available at: https://github.com/RuiLin0212/C2FLRTC.