DAVANet: Stereo Deblurring with View Aggregation

TL;DR

This paper introduces DAVANet, a novel stereo image deblurring network that leverages depth cues and view aggregation to effectively remove complex blur in dynamic scenes, supported by a large-scale dataset.

Contribution

The paper presents DAVANet, integrating depth awareness and view aggregation for stereo deblurring, and provides a large multi-scene dataset for benchmarking.

Findings

DAVANet outperforms existing methods in accuracy, speed, and model size.

The dataset contains over 20,000 stereo image pairs from diverse scenes.

Depth cues and view aggregation improve deblurring quality.

Abstract

Nowadays stereo cameras are more commonly adopted in emerging devices such as dual-lens smartphones and unmanned aerial vehicles. However, they also suffer from blurry images in dynamic scenes which leads to visual discomfort and hampers further image processing. Previous works have succeeded in monocular deblurring, yet there are few studies on deblurring for stereoscopic images. By exploiting the two-view nature of stereo images, we propose a novel stereo image deblurring network with Depth Awareness and View Aggregation, named DAVANet. In our proposed network, 3D scene cues from the depth and varying information from two views are incorporated, which help to remove complex spatially-varying blur in dynamic scenes. Specifically, with our proposed fusion network, we integrate the bidirectional disparities estimation and deblurring into a unified framework. Moreover, we present a large-scale multi-scene dataset for stereo deblurring, containing 20,637 blurry-sharp stereo image pairs from 135 diverse sequences and their corresponding bidirectional disparities. The experimental results on our dataset demonstrate that DAVANet outperforms state-of-the-art methods in terms of accuracy, speed, and model size.