Image deblurring using inertial measurement sensors

TLDR

The paper proposes a deblurring algorithm that uses a hardware attachment and a natural image prior to restore images from consumer cameras. The method estimates camera motion from inexpensive gyroscopes and accelerometers using an energy‑optimization framework, solves for high‑rate motion during exposure, and jointly optimizes to recover the latent image, with ground‑truth measurements used to validate the hardware and deconvolution. The algorithm automatically handles per‑pixel, spatially‑varying blur, supports kernels up to 100 pixels, outperforms leading image‑based methods, and is the first to use 6‑DOF inertial sensors for dense deblurring and to collect dense ground‑truth camera‑shake data.

Abstract

We present a deblurring algorithm that uses a hardware attachment coupled with a natural image prior to deblur images from consumer cameras. Our approach uses a combination of inexpensive gyroscopes and accelerometers in an energy optimization framework to estimate a blur function from the camera's acceleration and angular velocity during an exposure. We solve for the camera motion at a high sampling rate during an exposure and infer the latent image using a joint optimization. Our method is completely automatic, handles per-pixel, spatially-varying blur, and out-performs the current leading image-based methods. Our experiments show that it handles large kernels -- up to at least 100 pixels, with a typical size of 30 pixels. We also present a method to perform "ground-truth" measurements of camera motion blur. We use this method to validate our hardware and deconvolution approach. To the best of our knowledge, this is the first work that uses 6 DOF inertial sensors for dense, per-pixel spatially-varying image deblurring and the first work to gather dense ground-truth measurements for camera-shake blur.