A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
Modeling Blurred Video with Layers
[chapter]
2014
Lecture Notes in Computer Science
Preserved Fulltext
We address this with a novel layered model of scenes in motion. From a motion-blurred video sequence, we jointly estimate the layer segmentation and each layer's appearance and motion. ...
Since the blur is a function of the layer motion and segmentation, it is completely determined by our generative model. ...
Adelson for insights into motion blur and layers, and R. Zavada for the JFK video. ...
doi:10.1007/978-3-319-10599-4_16
fatcat:rre7ovcpafguzmpo2mgnqc2zdq
Occlusion-Aware Video Deblurring with a New Layered Blur Model
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We present a deblurring method for scenes with occluding objects using a carefully designed layered blur model. ...
Layered blur model is frequently used in the motion deblurring problem to handle locally varying blurs, which is caused by object motions or depth variations in a scene. ...
Proposed Layered Blur Model Here we propose a new layered blur model. ...
arXiv:1611.09572v1
fatcat:jqq2y5psazcyvbl7j5mruvdal4
Dataset and Network Structure: Towards Frames Selection for Fast Video Deblurring
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Wulff and Black [58] presented a double-layered blur model that can have different blur statuses in the front and back layer segments. Kohler et al. ...
[62] introduced REDs dataset, which consists of 330 video pairs, each video with 100 frames, he claimed that the used data degradation model can produce more realistic motion blur. Su et al. ...
doi:10.1109/access.2021.3074199
fatcat:jcqk6tkydnbkhcn6opgnpkjzja
Privacy-Aware Activity Classification from First Person Office Videos
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We utilized a Mask-RCNN with an Inception-ResNet hybrid as a feature extractor for detecting, and then blurring out sensitive objects (e.g., digital screens, human face, paper) from the videos. ...
On privacy protected videos, the performances were slightly degraded, with accuracy, precision, recall, and F1 scores at 73.68%, 0.79, 0.75, and 0.74, respectively. ...
The authors of [29] used AlexNet [30] as the feature extractor with two uni-directional LSTM layers for temporal sequence modeling. ...
arXiv:2006.06246v1
fatcat:hhvslmca4nbqxde72zuov263s4
Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition
2018
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2016 pre-print arXiv:1607.05427v1 fatcat:id2w7kivwbdidcoxov6gzzxqt4Other Versions
With the proposed techniques, we also obtain the first place in the BTAS 2016 Video Person Recognition Evaluation. ...
TBE-CNN is an end-to-end model that extracts features efficiently by sharing the low- and middle-level convolutional layers between the trunk and branch networks. ...
[9] proposed pre-training CNN models with a large volume of still face images and then fine-tuning the CNN models with small real-world video databases. ...
doi:10.1109/tpami.2017.2700390
pmid:28475048
fatcat:upxmdoqzo5dnri5zn6sdm7xnmi
Contiguous Loss for Motion-Based, Non-Aligned Image Deblurring
2021
Symmetry
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Experimental results show that the proposed model combined with the contiguous blurry loss can generate sharp video sequences efficiently and perform better than state-of-the-art methods. ...
Moreover, a blurry image does not have one-to-one correspondence with any sharp video sequence, since different video sequences can create similar blurry images, so neither the traditional pixel2pixel ...
Our D model consists of 16 convolution layers and one top layer with a bidirectional soft-max classifier. ...
doi:10.3390/sym13040630
fatcat:2rwr3ndp7jaa7lv55zkgmrsbjq
Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The proposed blur model is based on the non-linear optical flow, which describes complex motion blur more effectively. ...
Video deblurring is a challenging problem as the blur is complex and usually caused by the combination of camera shakes, object motions, and depth variations. ...
To deal with complex motion blurs, layered blur model is developed in the deblurring problem to handle locally varying blurs [5, 39] . Cho et al. ...
arXiv:1708.03423v1
fatcat:ztfjqbiyajcubatwzihhvmbrxe
Video Deblurring via Semantic Segmentation and Pixel-Wise Non-linear Kernel
2017
2017 IEEE International Conference on Computer Vision (ICCV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The proposed blur model is based on the non-linear optical flow, which describes complex motion blur more effectively. ...
Video deblurring is a challenging problem as the blur is complex and usually caused by the combination of camera shakes, object motions, and depth variations. ...
To deal with complex motion blurs, layered blur model is developed in the deblurring problem to handle locally varying blurs [5, 39] . Cho et al. ...
doi:10.1109/iccv.2017.123
dblp:conf/iccv/RenPC017
fatcat:cvz7fjcrwrfqzipu63tzxre5vm
Online Video Deblurring via Dynamic Temporal Blending Network
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
State-of-the-art video deblurring methods are capable of removing non-uniform blur caused by unwanted camera shake and/or object motion in dynamic scenes. ...
In doing so, our network is able to remove even large blur caused by strong camera shake and/or fast moving objects. ...
Wulff and Black [37] consider differently blurred bi-layered scenes and estimate segment-wise accurate blur kernels by constraining those through a temporally consistent affine motion model. ...
arXiv:1704.03285v1
fatcat:jkfg6cdkeba6ncizkokr5g2ti4
Spatio-Temporal Filter Adaptive Network for Video Deblurring
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2019 pre-print arXiv:1904.12257v1 fatcat:l7q2vap2r5gyjhumrtjssqzlxi
We then propose the new Filter Adaptive Convolutional (FAC) layer to align the deblurred features of the previous frame with the current frame and remove the spatially variant blur from the features of ...
of accuracy, speed as well as model size. ...
The algorithms by [42] and [32] use the predicted optical flow to segment layers with different blur and estimate the blur layer-by-layer. In addition, Kim et al. ...
arXiv:1904.12257v2
fatcat:253n774rnnhc5nhbvo7iug4kti
Transfer Learning and Decision Fusion for Real Time Distortion Classification in Laparoscopic Videos
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This challenging dataset contains videos that have five types of distortions such as noise, smoke, uneven illumination, defocus blur, and motion blur with four levels of intensity. ...
It is done with the aid of a video camera. Laparoscopic videos are affected by various distortions during surgery which lead to loss of visual quality. ...
The VGG model created by the Visual Geometry Group from the University of Oxford used a very deep CNN with 16 weight layers, 13 of which were convolutional layers with 3 × 3 filters, while three were fully ...
doi:10.1109/access.2021.3105454
fatcat:6atlrnzkcraenholfgxgxy4boe
Spatio-temporal deep learning model for distortion classification in laparoscopic video
2021
F1000Research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The laparoscopic video is prone to various distortions such as noise, smoke, uneven illumination, defocus blur, and motion blur. ...
Additionally, the proposed distortion identification model is able to run in real-time with low inference time (0.15 sec). ...
The numbers of videos for each label or distortion are not balanced (300 videos with AWGN, 320 videos with smoke, 400 videos with uneven illumination, 160 videos with defocus blur, 80 videos with motion ...
doi:10.12688/f1000research.72980.1
fatcat:bzbc4smonbe7dayge64xqyweru
Vehicle Classification with Convolutional Neural Network on Motion Blurred Images
2017
DEStech Transactions on Computer Science and Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
However, the trained model achieves poor performance on motion blurred images captured from videos. This paper proposes a new method for dealing with motion blurred images. ...
Random blurred images are generated during training in order to optimize the network parameters. ...
However, the trained model achieves poor performance on motion blurred images captured from videos. This paper proposes a new method for dealing with motion blurred images. ...
doi:10.12783/dtcse/aiea2017/14912
fatcat:jzksqhp7mzbcpobplgypndzurq
Learning to Synthesize Motion Blur
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We additionally capture a high quality test set of real motion blurred images, synthesized from slow motion videos, with which we evaluate our model against several baseline techniques that can be used ...
To build this system we motivate and design a differentiable "line prediction" layer to be used as part of a neural network architecture, with which we can learn a system to regress from image pairs to ...
Direct Prediction: instead of using line prediction our network directly estimates the motion blurred image, by replacing our line prediction model with a single 1×1 conv layer that produces a 3 channel ...
doi:10.1109/cvpr.2019.00700
dblp:conf/cvpr/BrooksB19
fatcat:rwphouqiyratxbmeluacvn5laq
Video Deblurring via Temporally and Spatially Variant Recurrent Neural Network
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
However, it is hard to recover sharp videos using existing single or multiple image deblurring methods, as the blur artifacts in blurry videos are both temporally and spatially varying. ...
Meanwhile, the proposed model is trained in an end-to-end manner, where the model input and output are set to the same number. ...
VIDEO DEBLURRING Compared with image deblurring, video deblurring is more challenging as it needs consider the problem of modeling temporal information. ...
doi:10.1109/access.2019.2962505
fatcat:ppivl5qz2baufgyy5cntoju3k4
« Previous
Showing results 1 — 15 out of 37,793 results