Filters








66 Hits in 3.9 sec

Robust Single Image Deblurring Using Gyroscope Sensor

Seowon Ji, Jun-Pyo Hong, Jeongmin Lee, Seung-Jin Baek, Sung-Jea Ko
2021 IEEE Access  
Using a new gyro-image paired dataset, extensive experiments were conducted to show the effects of the reliability of the gyroscope measurements on the deblurring performance and to prove the effectiveness  ...  Motion blur in an image is caused by the movement of the camera during exposure time; thus, awareness of the camera motion is a key factor in image deblurring algorithms.  ...  The authors thank Cheol-Hwan Yoo of Korea University for capturing image-gyro paired dataset.  ... 
doi:10.1109/access.2021.3084968 fatcat:uqnbrtuoqfg7phdxwacu5n5kzm

Gyroscope-Aided Motion Deblurring with Deep Networks [article]

Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä
2018 arXiv   pre-print
At the same time, the image data is used to overcome the limitations of gyro-based blur estimation.  ...  We propose a deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN).  ...  Our work deals with inertial-aided single-image deblurring.  ... 
arXiv:1810.00986v2 fatcat:xjgylv25dfhizi52ieyd265dme

Gyroscope-Aided Motion Deblurring with Deep Networks

Janne Mustaniemi, Juho Kannala, Simo Sarkka, Jiri Matas, Janne Heikkila
2019 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)  
At the same time, the image data is used to overcome the limitations of gyro-based blur estimation.  ...  We propose a deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN).  ...  There have been relatively many papers that utilize inertial sensors (gyroscopes and/or accelerometers) for image deblurring [10, 7, 6, 31, 14, 20] .  ... 
doi:10.1109/wacv.2019.00208 dblp:conf/wacv/MustaniemiKSMH19 fatcat:opmypn3anjfxdflld5my4pz5my

Gyro-Based Multi-image Deconvolution for Removing Handshake Blur

Sung Hee Park, Marc Levoy
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper we analyze multi-image approaches, which capture and combine multiple frames in order to make deblurring more robust and tractable.  ...  Image deblurring to remove blur caused by camera shake has been intensively studied. Nevertheless, most methods are brittle and computationally expensive.  ...  On the other hand, image deblurring uses a long exposure time to capture a clean but blurry image and recovers the sharp image using deblurring.  ... 
doi:10.1109/cvpr.2014.430 dblp:conf/cvpr/ParkL14 fatcat:jdlnwnf7mzhmdkk7wodairqnli

SID: Sensor-assisted Image Deblurring System for Mobile Devices

Qing Wang, Jun Tan, Tianzhang Xing, Feng Chen, Jinping Niu
2019 IEEE Access  
In this paper, we present SID, a sensor-assisted image deblurring system for mobile devices.  ...  Using information about camera motion acquired from built-in sensors from smartphones (e.g. accelerometers, gyroscopes, and magnetometers), then estimating the point spread function, and combining the  ...  However, due to drift problems with noise sensor reading, efficient image deblurring cannot be performed using a single sensor data.  ... 
doi:10.1109/access.2019.2937137 fatcat:niz2nwqurrhthbgcpbucluo24q

Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements [article]

Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä
2018 arXiv   pre-print
We propose an inertial-based deblurring method for improving the robustness of existing feature detectors and descriptors against the motion blur.  ...  The limitations of inertial-based blur estimation are taken into account by validating the blur estimates using image data.  ...  However, it still uses a feature detector that is not robust to motion blur.  ... 
arXiv:1805.08542v1 fatcat:lbnjxr4i3vgwjf6sbwdctkjvdu

Dense 3D Reconstruction from Severely Blurred Images Using a Single Moving Camera

Hee Seok Lee, Kuoung Mu Lee
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
Motion blur frequently occurs in dense 3D reconstruction using a single moving camera, and it degrades the quality of the 3D reconstruction.  ...  The obtained blur kernel is depth-dependent, thus it effectively addresses scene-depth variation, which is a challenging problem in conventional non-uniform deblurring methods.  ...  Their depthdependent blur kernel estimation can be extended to single image deblurring, however, camera motion is limited to translation in single image cases.  ... 
doi:10.1109/cvpr.2013.42 dblp:conf/cvpr/LeeL13 fatcat:wt7mvzblc5h5pexdhj47gesiae

A Comparative Study for Single Image Blind Deblurring

Wei-Sheng Lai, Jia-Bin Huang, Zhe Hu, Narendra Ahuja, Ming-Hsuan Yang
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We present the first comprehensive perceptual study and analysis of single image blind deblurring using real-world blurred images.  ...  Numerous single image blind deblurring algorithms have been proposed to restore latent sharp images under camera motion.  ...  To synthesize non-uniform blurred images, we record the 6D camera trajectories using a cellphone with inertial sensors (gyroscope and accelerometer), and construct a collection of spatially varying blur  ... 
doi:10.1109/cvpr.2016.188 dblp:conf/cvpr/LaiHHA016 fatcat:j7ynwpf2ubdjjewb4pzud2djfe

Inertia Sensor Aided Alignment for Burst Pipeline in Low Light Conditions

Shuang Zhang, Robert L. Stevenson
2018 2018 25th IEEE International Conference on Image Processing (ICIP)  
We compare the proposed method to benchmark single-image and multi-image denoising methods with favorable results.  ...  Merging short-exposure frames can provide an image with reduced noise in low light conditions. However, how best to align images before merging is an open problem.  ...  Comparison with BM3D can provide us the denoising effect between best conventional single-image (according to [15] ) and novel multi-images denoising methods.  ... 
doi:10.1109/icip.2018.8451134 dblp:conf/icip/ZhangS18 fatcat:mqvk25qzmffjvkjhac53fwoyt4

Occlusion Detection and Index-based Ear Recognition

Madeena Sultana, Padma Polash Paul, Marina Gavrilova
2015 Journal of WSCG  
An international journal of algorithms, data structures and techniques for computer graphics and visualization, surface meshing and modeling, global illumination, computer vision, image processing and  ...  Ideally, the recorded image and the generated image should look identical, and after (single-frame) deblurring using the generated kernels the resulting image should show a point light grid again.  ...  Next, we perform single-frame deblurring on every B j as well as B to get sharper estimates Ĩ j and Ĩ, respectively. After deblurring the single frames, we align all sharpened estimates with Ĩ.  ... 
dblp:journals/jwscg/SultanaPG15 fatcat:uisp4vxs2vecrpjyy6cugbd2oa

Temporal-Spatial Consistency and Sampling Neural Network Based Adaptive Hand-held Video Deblurring

Xiao LI, Shuai LI, Hong QIN, Ai-min HAO
2019 DEStech Transactions on Computer Science and Engineering  
Video deblurring for hand-held camera is vital in many high-level video enhancement applications.  ...  Our aim is to devise a new adaptive video deblurring technique by resorting to new modeling strategies.  ...  Fusion Based Deblurring Image fusion method produces a single image from a set of input images.  ... 
doi:10.12783/dtcse/iteee2019/28728 fatcat:qmp4iahzefeoti7qo4qjvwpldu

Low-light Image Restoration with Short- and Long-exposure Raw Pairs [article]

Meng Chang, Huajun Feng, Zhihai Xu, Qi Li
2021 arXiv   pre-print
In this paper, we propose a new low-light image restoration method by using the complementary information of short- and long-exposure images.  ...  Using our data generation method and the proposed LSFNet, we can recover the details and color of the original scene, and improve the low-light image quality effectively.  ...  However, single-image deblurring methods are difficult to have good robustness due to the diversity of motion blur.  ... 
arXiv:2007.00199v2 fatcat:jtx63ph23jbf7ht5rdr3ecmdhm

Coded exposure photography

Ramesh Raskar, Amit Agrawal, Jack Tumblin
2006 ACM Transactions on Graphics  
a) Blurred Image (b) Rectified Crop (c) Deblurred Image Figure 1: Coded exposure enables recovery of fine details in the deblurred image. (a) Photo of a fast moving vehicle.  ...  (c) Deblurred result. Note that all sharp features on the vehicle (such as text) have been recovered.  ...  Our system can deblur the image to the extent of the motion within a single chop. Let us compare to an image captured with an exposure of a single chop, which is equal to T /m seconds.  ... 
doi:10.1145/1141911.1141957 fatcat:oyomx53n2jfx7l4nu6dk3wef4e

A visually guided swimming robot

G. Dudek, M. Jenkin, C. Prahacs, A. Hogue, J. Sattar, P. Giguere, A. German, Hui Liu, S. Saunderson, A. Ripsman, S. Simhon, L.-A. Torres (+3 others)
2005 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems  
Designed to rely primarily on visual sensors, the AQUA robot uses vision to navigate underwater using servobased guidance, and also to obtain high-resolution range scans of its local environment.  ...  This paper describes some of the pragmatic and logistic obstacles encountered, and provides an overview of some of the basic capabilities of the vehicle and its associated sensors.  ...  In our case, these pairs are the images we actually observe and corresponding color-corrected and deblurred images.  ... 
doi:10.1109/iros.2005.1545231 dblp:conf/iros/DudekJPHSGGLSRSTMZR05 fatcat:fy4rifsdlvgtrp5omc3igqz4ia

Bringing Alive Blurred Moments [article]

Kuldeep Purohit, Anshul Shah, A. N. Rajagopalan
2019 arXiv   pre-print
As an intermediate step, we also design an efficient architecture that enables real-time single image deblurring and outperforms competing methods across all factors: accuracy, speed, and compactness.  ...  We present a solution for the goal of extracting a video from a single motion blurred image to sequentially reconstruct the clear views of a scene as beheld by the camera during the time of exposure.  ...  The potential of our work can be extended in a variety of directions including blur-based segmentation, video deblurring, video interpolation, action recognition etc.  ... 
arXiv:1804.02913v2 fatcat:2fv7f7bsazbqjieysood5jitza
« Previous Showing results 1 — 15 out of 66 results