Gyroscope-Assisted Motion Deblurring Network
This addresses the problem of limited real-world deblurring performance for computer vision applications by providing a method to generate realistic training data, though it is incremental as it builds on existing deblurring networks.
The paper tackles motion blur image restoration by using Inertial Measurement Unit (IMU) data to generate synthetic training triplets and proposes a Gyroscope-Aided Motion Deblurring (GAMD) network, achieving a 33.17% improvement in PSNR over the state-of-the-art method MIMO.
Image research has shown substantial attention in deblurring networks in recent years. Yet, their practical usage in real-world deblurring, especially motion blur, remains limited due to the lack of pixel-aligned training triplets (background, blurred image, and blur heat map) and restricted information inherent in blurred images. This paper presents a simple yet efficient framework to synthetic and restore motion blur images using Inertial Measurement Unit (IMU) data. Notably, the framework includes a strategy for training triplet generation, and a Gyroscope-Aided Motion Deblurring (GAMD) network for blurred image restoration. The rationale is that through harnessing IMU data, we can determine the transformation of the camera pose during the image exposure phase, facilitating the deduction of the motion trajectory (aka. blur trajectory) for each point inside the three-dimensional space. Thus, the synthetic triplets using our strategy are inherently close to natural motion blur, strictly pixel-aligned, and mass-producible. Through comprehensive experiments, we demonstrate the advantages of the proposed framework: only two-pixel errors between our synthetic and real-world blur trajectories, a marked improvement (around 33.17%) of the state-of-the-art deblurring method MIMO on Peak Signal-to-Noise Ratio (PSNR).