Adobe Working on Cool New Deblurring Tool for Your Video Footage
Last week we covered a wonderful story about a terrific new feature in the latest Photoshop CC release: the Camera Shake Reduction Tool, which was previously known as Photoshop Image Deblurring. This new capability has received a lot of press and attention – and, as shown in our previous article, it can really make a difference.
But accomplishing this feat for still images isn’t the only cool deblurring application Adobe has been working on lately… Adobe researcher Jue Wang has published a paper on an innovative new technique to deblur videos as well – which could be huge considering how much handheld video footage is out there now, and growing every day. The development of this technology could be a big addition to flagship video editing tools like Adobe’s Premiere Pro.
Here’s the summary:
Video Deblurring for Hand-held Cameras Using Patch-based Synthesis
Videos captured by hand-held cameras often contain significant camera shake, causing many frames to be blurry. Restoring shaky videos not only requires smoothing the camera motion and stabilizing the content, but also demands removing blur from video frames. However, video blur is hard to remove using existing single or multiple image deblurring techniques, as the blur kernel is both spatially and temporally varying.
This paper presents a video deblurring method that can effectively restore sharp frames from blurry ones caused by camera shake. Our method is built upon the observation that due to the nature of camera shakes, not all video frames are equally blurry. The same object may appear sharp on some frames while blurry on others. Our method detects sharp regions in the video, and uses them to restore blurry regions of the same content in nearby frames. Our method also ensures that the deblurred frames are both spatially and temporally coherent using patch-based synthesis. Experimental results show that our method can effectively remove complex video blur under the presence of moving objects and other outliers, which cannot be achieved using previous deconvolution-based approaches.
And check out this demo to see some of the very impressive results of the work:
Now, will we see this technology part of the upcoming Creative Cloud 2014 Release? It’s hard to say for sure from what’s been presented – but if things goes like they did for Image Deblurring, then we may see a ‘sneak peek’ presented at Adobe MAX in the fall, and then hopefully incorporated into Premiere in a future version.
Right now, the biggest challenge seems to be the time needed to process and perform the video deblurring function, which is said to be about one minute per HD frame on an Intel Core i7 system, according to the researcher’s conference presentation. However, he added that he believes the technology is easily parallelizable, which may make it a good candidate for a cloud-based service.
And considering the Adobe CEO once said that sophisticated deblurring technology may be available only through a cloud service, that approach would be consistent.
What’s your view – would you like to see a capability like this in a future release of Premiere Pro? Let us know your thoughts in the comments below.