Proceedings ArticleDOI
Intra-frame deblurring by leveraging inter-frame camera motion
Haichao Zhang,Jianchao Yang +1 more
- pp 4036-4044
Reads0
Chats0
TLDR
The proposed video deblurring method effectively leverages the information distributed across multiple video frames due to camera motion, jointly estimating the motion between consecutive frames and blur within each frame.Abstract:
Camera motion introduces motion blur, degrading the quality of video. A video deblurring method is proposed based on two observations: (i) camera motion within capture of each individual frame leads to motion blur; (ii) camera motion between frames yields inter-frame mis-alignment that can be exploited for blur removal. The proposed method effectively leverages the information distributed across multiple video frames due to camera motion, jointly estimating the motion between consecutive frames and blur within each frame. This joint analysis is crucial for achieving effective restoration by leveraging temporal information. Extensive experiments are carried out on synthetic data as well as real-world blurry videos. Comparisons with several state-of-the-art methods verify the effectiveness of the proposed method.read more
Citations
More filters
Proceedings ArticleDOI
Online Video Deblurring via Dynamic Temporal Blending Network
TL;DR: In this paper, a spatio-temporal recurrent network is proposed for real-time video deblurring, which extends the receptive field while keeping the overall size of the network small to enable fast execution.
Book ChapterDOI
Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks
Miika Aittala,Frédo Durand +1 more
TL;DR: The novel convolutional architecture has a simultaneous view of all frames in the burst, and by construction treats them in an order-independent manner to effectively detect and leverage subtle cues scattered across different frames, while ensuring that each frame gets a full and equal consideration regardless of its position in the sequence.
Book ChapterDOI
Spatio-Temporal Transformer Network for Video Restoration
Tae Hyun Kim,Tae Hyun Kim,Mehdi S. M. Sajjadi,Michael Hirsch,Michael Hirsch,Bernhard Schölkopf +5 more
TL;DR: A novel Spatio-temporal Transformer Network (STTN) is proposed which handles multiple frames at once and thereby manages to mitigate the common nuisance of occlusions in optical flow estimation.
Proceedings ArticleDOI
Learning to Extract a Video Sequence from a Single Motion-Blurred Image
TL;DR: In this article, the authors propose a method to extract a video sequence from a single motion-blurred image using a deep learning scheme that gradually reconstructs a temporal ordering by sequentially extracting pairs of frames.
Proceedings ArticleDOI
Learning Blind Motion Deblurring
TL;DR: This work proposes an efficient approach to produce a significant amount of realistic training data and introduces a novel recurrent network architecture to deblur frames taking temporal information into account, which can efficiently handle arbitrary spatial and temporal input sizes.
References
More filters
Journal ArticleDOI
Removing camera shake from a single photograph
TL;DR: This work introduces a method to remove the effects of camera shake from seriously blurred images, which assumes a uniform camera blur over the image and negligible in-plane camera rotation.
Proceedings ArticleDOI
Secrets of optical flow estimation and their principles
TL;DR: It is discovered that “classical” flow formulations perform surprisingly well when combined with modern optimization and implementation techniques, and while median filtering of intermediate flow fields during optimization is a key to recent performance gains, it leads to higher energy solutions.
Proceedings ArticleDOI
Image and depth from a conventional camera with a coded aperture
TL;DR: A simple modification to a conventional camera is proposed to insert a patterned occluder within the aperture of the camera lens, creating a coded aperture, and introduces a criterion for depth discriminability which is used to design the preferred aperture pattern.
Journal ArticleDOI
High-quality motion deblurring from a single image
Qi Shan,Jiaya Jia,Aseem Agarwala +2 more
TL;DR: A new algorithm for removing motion blur from a single image is presented using a unified probabilistic model of both blur kernel estimation and unblurred image restoration and is able to produce high quality deblurred results in low computation time.
Journal ArticleDOI
Fast motion deblurring
Sunghyun Cho,Seungyong Lee +1 more
TL;DR: A fastdeblurring method that produces a deblurring result from a single image of moderate size in a few seconds by introducing a novel prediction step and working with image derivatives rather than pixel values, which gives faster convergence.