When you take move the camera while taking a photo you get motion blur. At this years Siggraph conference there are several papers about how to remove motion blur from images. Take a look at this paper High-quality Motion Deblurring from a Single Image that uses a single blurry image as source and makes a virtually perfect photo. The screenshots are quite amazing. As people from Abobe are part of the paper we can hopefully sees this as a filter in future versions of photoshop.
Using this teqnique together with a video frame capture software like fast video indexer could create really awsome screenshots from videos.
The abstract for the paper:
"We present a new algorithm for removing motion blur from a single image. Our method computes a deblurred image using a unified probabilistic model of both blur kernel estimation and unblurred image restoration. We present an analysis of the causes of common artifacts found in current deblurring methods, and then introduce several novel terms within this probabilistic model that are inspired by our analysis. These terms include a model of the spatial randomness of noise in the blurred image, as well a new local smoothness prior that reduces ringing artifacts by constraining contrast in the unblurred image wherever the blurred image exhibits low contrast. Finally, we describe an efficient optimization scheme that alternates between blur kernel estimation and unblurred image restoration until convergence. As a result of these steps, we are able to produce high quality deblurred results in low computation time. We are even able to produce results of comparable quality to techniques that require additional input images beyond a single blurry photograph, and to methods that require additional hardware."
Using this teqnique together with a video frame capture software like fast video indexer could create really awsome screenshots from videos.
The abstract for the paper:
"We present a new algorithm for removing motion blur from a single image. Our method computes a deblurred image using a unified probabilistic model of both blur kernel estimation and unblurred image restoration. We present an analysis of the causes of common artifacts found in current deblurring methods, and then introduce several novel terms within this probabilistic model that are inspired by our analysis. These terms include a model of the spatial randomness of noise in the blurred image, as well a new local smoothness prior that reduces ringing artifacts by constraining contrast in the unblurred image wherever the blurred image exhibits low contrast. Finally, we describe an efficient optimization scheme that alternates between blur kernel estimation and unblurred image restoration until convergence. As a result of these steps, we are able to produce high quality deblurred results in low computation time. We are even able to produce results of comparable quality to techniques that require additional input images beyond a single blurry photograph, and to methods that require additional hardware."
Inga kommentarer:
Skicka en kommentar