Exploring and Evaluating Image Restoration Potential in Dynamic Scenes

TL;DR

This paper introduces the concept of image restoration potential (IRP) in dynamic scenes, proposing a dataset and a deep model to predict IRP, which can enhance image restoration, frame selection, and camera setting optimization.

Contribution

The paper presents the first study on IRP, including a new dataset and a deep learning model for accurate IRP prediction, enabling improved restoration and camera parameter tuning.

Findings

IRP can be effectively predicted using the proposed deep model.

IRP prediction benefits frame filtering and restoration quality.

IRP serves as a useful indicator for camera setting optimization.

Abstract

In dynamic scenes, images often suffer from dynamic blur due to superposition of motions or low signal-noise ratio resulted from quick shutter speed when avoiding motions. Recovering sharp and clean results from the captured images heavily depends on the ability of restoration methods and the quality of the input. Although existing research on image restoration focuses on developing models for obtaining better restored results, fewer have studied to evaluate how and which input image leads to superior restored quality. In this paper, to better study an image's potential value that can be explored for restoration, we propose a novel concept, referring to image restoration potential (IRP). Specifically, We first establish a dynamic scene imaging dataset containing composite distortions and applied image restoration processes to validate the rationality of the existence to IRP. Based on this dataset, we investigate several properties of IRP and propose a novel deep model to accurately predict IRP values. By gradually distilling and selective fusing the degradation features, the proposed model shows its superiority in IRP prediction. Thanks to the proposed model, we are then able to validate how various image restoration related applications are benefited from IRP prediction. We show the potential usages of IRP as a filtering principle to select valuable frames, an auxiliary guidance to improve restoration models, and even an indicator to optimize camera settings for capturing better images under dynamic scenarios.