Full-frame video stabilization with motion inpainting

By Yasuyuki Matsushita, Eyal Ofek, Weina Ge, Xiaoou Tang, Harry Shum. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006

604 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/46d031105223d2c0a8ad99e7fc0e6210e1e22596

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

Spatio-Temporal Filter Adaptive Network for Video Deblurring (2019, background): “Significant progress has been made due to the use of sharper regions from neighboring frames [20, 3] or the optical flow from consecutive frames [9, 32].”
Online Video Deblurring via Dynamic Temporal Blending Network (2017, methodology): “[25] detected sharp frames using image statistics, performed global image registration and transferred pixel intensities from neighboring sharp frames to blurry ones in order to remove blur.”
Deep Video Deblurring for Hand-Held Cameras (2017, positive): “Sharp pixels thus can be transferred from nearby frames to deblur the target frame, using for example homography alignment [30].”
First-person hyper-lapse videos (2014, methodology): “Traditional video stabilization techniques use parameteric global transforms such as translations and rotations (optionally followed by local refinements), since these can be estimated quickly and robustly [Matsushita et al. 2006].”
Auto-directed video stabilization with robust L1 optimal camera paths (2011, methodology): “In general, post-process video stabilization [10] consists of the following three main steps: (1) Estimating the original (potentially shaky) camera path, (2) Estimating a new smooth camera path, and (3) Synthesizing the stabilized video using the estimated smooth camera path.”
Learning Joint Spatial-Temporal Transformations for Video Inpainting (2020, background): “gions in video frames with plausible contents [2]. An eective video inpainting algorithm has a wide range of practical applications, such as corrupted video restoration [10], unwanted object removal [22,26], video retargeting [16] and under/over-exposed image restoration [18]. Despite of the huge be”
Deep Video Inpainting (2019, methodology): “To address the temporal consistency, several methods have been developed to fill in the missing motion fields; using a greedy selection of local spatio-temporal patches [24], a per-frame diffusion-based technique [16], or an iterative optimization [11].”
Hand-Held Video Deblurring Via Efficient Fourier Aggregation (2015, background): “[37] propose to transfer, by interpolation, sharp image pixels from nearby frames to increase the sharpness of the blurry ones.”
Content-preserving warps for 3D video stabilization (2009, methodology): “Finally, there are a number of orthogonal issues in video stabilization that we do not address [Matsushita et al. 2006], such as removing motion blur, and full-frame video stabilization that avoids the loss of information at the video boundaries via hole-filling (we simply crop our output).”