CVPR 2007 · Oral presentation Computational photography
Resolving Objects at Higher Resolution from a Single Motion-Blurred Image
The idea
Use motion blur to
recover finer detail.
A single motion-blurred image can contain information for increasing the resolution of a moving object. Coded exposure preserves high spatial frequencies, allowing deblurring and resolution enhancement to be solved together with a linear algorithm.
- One captured image
- Recover detail from a single motion-blurred photograph
- Up to 4× enhancement
- Demonstrated on real images in the paper
- No training images
- Uses the captured information without image priors
- Selective enhancement
- Increase resolution in a narrow region when motion is limited
Deblurring and
super-resolution
Motion deblurring with a traditional camera is ill-posed. The flutter shutter camera, introduced in our SIGGRAPH 2006 work, preserves spatial frequencies and makes deblurring well-posed.
This paper extends the reconstruction problem to include resolution enhancement. The combined linear system remains ill-posed with traditional capture, while coded exposure improves its conditioning.
Larger motion blur can support a greater resolution increase, with a corresponding increase in reconstruction noise. When the blur is too small to enhance the entire object, the method can selectively enhance a narrow region containing high-frequency features.
Abstract
Motion blur can degrade the quality of images and is considered a nuisance for computer vision problems. In this paper, we show that motion blur can in fact be used for increasing the resolution of a moving object. Our approach utilizes the information in a single motion-blurred image without any image priors or training images. As the blur size increases, the resolution of the moving object can be enhanced by a larger factor, albeit with a corresponding increase in reconstruction noise.
Traditionally, motion deblurring and super-resolution have been ill-posed problems. Using a coded-exposure camera that preserves high spatial frequencies in the blurred image, we present a linear algorithm for the combined problem of deblurring and resolution enhancement and analyze the invertibility of the resulting linear system. We also show a method to selectively enhance the resolution of a narrow region of high-frequency features, when the resolution of the entire moving object cannot be increased due to small motion blur. Results on real images showing up to four times resolution enhancement are presented.