• Siddesh Kumar B
• Shilpa S N

Although spatial de-blurring is relatively well understood by assuming that the blur kernel is shift invariant, motion blur is not so when we attempt to deconvolve on a frame- by-frame basis, this is because, in general, videos include complex, multilayer transitions. Indeed, we face an exceedingly difficult problem in motion de-blurring of a single frame when the scene contains motion occlusions. Instead of de-blurring video frames individually, a fully 3-D de-blurring method is proposed in this work to reduce motion blur from a single motion-blurred video to produce a high-resolution video in both space and time. Unlike other existing approaches, the proposed de-blurring kernel is free from knowledge of the local motions. Most importantly, due to its inherent locally adaptive nature, the 3-D de-blurring is capable of automatically de-blurring the portions of the sequence, which are motion blurred, without segmentation and without adversely affecting the rest of the spatiotemporal domain, where such blur is not present. Our method is a two-step approach; first we upscale the input video in space and time without explicit estimates of local motions, and then perform 3-D de-blurring to obtain the restored sequence. A 3-D Point Spread Function is used to generate the deblurred video.

PSF, Deblur, Spatio

"Spatiotemporal (Motion) DeBlur using 3D PSF Filter", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.3, Issue 10, page no.173-179, October-2016, Available :http://www.jetir.org/papers/JETIR1701B32.pdf

"Spatiotemporal (Motion) DeBlur using 3D PSF Filter", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.3, Issue 10, page no. pp173-179, October-2016, Available at : http://www.jetir.org/papers/JETIR1701B32.pdf