Hand-Held Video Deblurring Via Efficient Fourier Aggregation

By Mauricio Delbracio, Guillermo Sapiro. 2015

70 citations recorded by the source corpus.

Videos captured with hand-held cameras often suffer from a significant amount of blur, mainly caused by the inevitable natural tremor of the photographer's hand. In this work, we present an algorithm that removes blur due to camera shake by combining information in the Fourier domain from nearby frames in a video. The dynamic nature of typical videos with the presence of multiple moving objects and occlusions makes this problem of camera shake removal extremely challenging, in particular when low complexity is needed. Given an input video frame, we first create a consistent registered version of temporally adjacent frames. Then, the set of consistently registered frames is blockwise fused in the Fourier domain with weights depending on the Fourier spectrum magnitude. The method is motivated from the physiological fact that camera shake blur has a random nature; therefore, nearby video frames are generally blurred differently. Experiments with numerous videos recorded in the wild, along with extensive comparisons, show that the proposed algorithm achieves state-of-the-art results while at the same time being much faster than its competitors.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric (2018, methodology): “Video deblurring We sample from the video deblurring dataset [52], along with deblurring outputs from Photoshop Shake Reduction, Weighted Fourier Aggregation [11], and three variants of a deep video deblurring method [52].”
Deep Stacked Hierarchical Multi-Patch Network for Image Deblurring (2019, unknown): “08 WFA [2] 25.”
Deep Video Deblurring for Hand-Held Cameras (2017, methodology): “Input (top) / ours (bottom) Input PSDEBLUR WFA[6] DBN+SINGLE DBN+NOALIGN DBN+HOMOG DBN+FLOW ground-truth 21.”
Online Video Deblurring via Dynamic Temporal Blending Network (2017, methodology): “Delbracio and Sapiro [9] also use bi-directional optical ﬂow for pixel-wise registration of consecutive frames, however manage to keep processing time low by using their fast FBA [8] method for local blur removal.”