DAVANet: Stereo Deblurring with View Aggregation
This addresses the issue of blurry images from stereo cameras in devices like smartphones and drones, which can cause visual discomfort and hinder image processing, representing a domain-specific advancement in computer vision.
The paper tackles the problem of deblurring stereo images in dynamic scenes, which is understudied compared to monocular deblurring, and proposes DAVANet, a network that integrates depth awareness and view aggregation to outperform state-of-the-art methods in accuracy, speed, and model size on a new large-scale dataset.
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.