Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements
This addresses the problem of degraded feature performance in vision applications like 3D reconstruction, offering a real-time solution, though it is incremental as it builds on existing deblurring and feature methods.
The paper tackles motion blur's negative impact on feature detection and matching in computer vision by proposing an inertial-based deblurring method that handles spatially-variant blur and rolling shutter distortion in real-time, resulting in increased keypoints, higher repeatability, and improved localization accuracy.
Many computer vision and image processing applications rely on local features. It is well-known that motion blur decreases the performance of traditional feature detectors and descriptors. We propose an inertial-based deblurring method for improving the robustness of existing feature detectors and descriptors against the motion blur. Unlike most deblurring algorithms, the method can handle spatially-variant blur and rolling shutter distortion. Furthermore, it is capable of running in real-time contrary to state-of-the-art algorithms. The limitations of inertial-based blur estimation are taken into account by validating the blur estimates using image data. The evaluation shows that when the method is used with traditional feature detector and descriptor, it increases the number of detected keypoints, provides higher repeatability and improves the localization accuracy. We also demonstrate that such features will lead to more accurate and complete reconstructions when used in the application of 3D visual reconstruction.