Digital Gimbal: End-to-end Deep Image Stabilization with Learnable Exposure Times
This work addresses the problem of motion blur in long-exposure photography for general users by offering a software-based alternative to bulky and expensive mechanical gimbals.
This paper proposes a digital method to stabilize images, emulating a mechanical gimbal by aggregating a burst of noisy short-exposure frames to produce a sharp, high-SNR image. The method also learns optimal exposure times for the burst, outperforming traditional single-image deblurring or fixed-exposure burst denoising on synthetic and real data.
Mechanical image stabilization using actuated gimbals enables capturing long-exposure shots without suffering from blur due to camera motion. These devices, however, are often physically cumbersome and expensive, limiting their widespread use. In this work, we propose to digitally emulate a mechanically stabilized system from the input of a fast unstabilized camera. To exploit the trade-off between motion blur at long exposures and low SNR at short exposures, we train a CNN that estimates a sharp high-SNR image by aggregating a burst of noisy short-exposure frames, related by unknown motion. We further suggest learning the burst's exposure times in an end-to-end manner, thus balancing the noise and blur across the frames. We demonstrate this method's advantage over the traditional approach of deblurring a single image or denoising a fixed-exposure burst on both synthetic and real data.