1,265 Hits in 4.2 sec

Improved Motion Invariant Deblurring through Motion Estimation [chapter]

Scott McCloskey
2014 Lecture Notes in Computer Science  
The key advantage of motion invariance is that, unlike other computational photographic techniques, it does not require pre-exposure velocity estimation in order to ensure numerically stable deblurring  ...  Surprisingly, despite the use of parabolic motion to capture an image in which blur is invariant to motion, we demonstrate that the motion invariant image can be used to estimate object motion post-capture  ...  In addition to Fig. 1 , the deblurred results in Fig. 8 show the improved image quality that we enable with our motion estimation algorithm.  ... 
doi:10.1007/978-3-319-10593-2_6 fatcat:kagtmzqwbjg5ppfczuvqkja2hi

Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes

Hyeongseok Son, Junyong Lee, Jonghyeop Lee, Sunghyun Cho, Seungyong Lee
2021 ACM Transactions on Graphics  
First, we present blur-invariant motion estimation learning to improve motion estimation accuracy between blurry frames.  ...  Second, for motion compensation, instead of aligning frames by warping with estimated motions, we use a pixel volume that contains candidate sharp pixels to resolve motion estimation errors.  ...  This work was supported by the Ministry of Science and ICT, Korea, through IITP grants (SW Star Lab, IITP-2015-0-00174; Artificial Intelligence Graduate School Program (POSTECH), IITP-2019-0-01906) and  ... 
doi:10.1145/3453720 fatcat:mulollrl2nhwferudbt37vxug4

Blur Invariant Kernel-Adaptive Network for Single Image Blind deblurring [article]

Sungkwon An, Hyungmin Roh, Myungjoo Kang
2020 arXiv   pre-print
Subsequently, we propose a deblurring network that restores sharp images using the estimated blur kernel.  ...  Our model solves the deblurring problem by dividing it into two successive tasks: (1) blur kernel estimation and (2) sharp image restoration.  ...  We checked the effect of the long-term skip connection on the performance improvement through ablation study in Section 4.  ... 
arXiv:2007.04543v3 fatcat:mhyenqhhjnd4roap6tzqkmo5za

Correction of Spatially Varying Image and Video Motion Blur Using a Hybrid Camera

Yu-Wing Tai, Hao Du, Michael S Brown, Stephen Lin
2010 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Our approach can reduce motion blur from the high-resolution video as well as estimate new high-resolution frames at a higher framerate.  ...  Experimental results on a variety of inputs demonstrate notable improvement over current state-of-the-art methods in image/video deblurring.  ...  to jointly improve global motion deblurring.  ... 
doi:10.1109/tpami.2009.97 pmid:20431128 fatcat:n5kfw4qz3fdjfmwllx7eohfpxi

Single Image Deblurring Using Motion Density Functions [chapter]

Ankit Gupta, Neel Joshi, C. Lawrence Zitnick, Michael Cohen, Brian Curless
2010 Lecture Notes in Computer Science  
We present a novel single image deblurring method to estimate spatially non-uniform blur that results from camera shake.  ...  We use existing spatially invariant deconvolution methods in a local and robust way to compute initial estimates of the latent image.  ...  We would also like to thank Qi Shan for useful discussions regarding blind/non-blind image deblurring methods.  ... 
doi:10.1007/978-3-642-15549-9_13 fatcat:lbwdv4wnbjet5plcx75ts53mzy

Interactive motion deblurring using light streaks

Binh-Son Hua, Kok-Lim Low
2011 2011 18th IEEE International Conference on Image Processing  
We propose a single-image, shift-invariant motion deblurring approach where the blur kernel is directly estimated from light streaks in the blurred image.  ...  This kernel can then be applied to state-of-the-art single-image motion deblurring methods to restore the sharp image.  ...  We assume that in a local neighborhood, the motion blur is shift-invariant.  ... 
doi:10.1109/icip.2011.6115743 dblp:conf/icip/HuaL11 fatcat:ekdbdtqezzdtnmlo4ubwdu465u

Coded exposure imaging for projective motion deblurring

Yu-Wing Tai, Naejin Kong, Stephen Lin, Sung Yong Shin
2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
We propose a method for deblurring of spatially variant object motion. A principal challenge of this problem is how to estimate the point spread function (PSF) of the spatially variant blur.  ...  With this spatially variant PSF, objects that exhibit projective motion can be effectively deblurred. We validate this method with several challenging image examples.  ...  Here, the PSF is obtained by estimating the length of horizontal motion along scribbles through detecting the two end points of gradient discontinuities.  ... 
doi:10.1109/cvpr.2010.5539935 dblp:conf/cvpr/TaiKLS10 fatcat:rnltrkwkqne63jmikfk444v6wm

Combining Motion Compensation with Spatiotemporal Constraint for Video Deblurring

Jing Li, Weiguo Gong, Weihong Li
2018 Sensors  
Secondly, we proposed a blur kernel estimation strategy by applying the derived motion-compensated frame to an improved regularization model for improving the quality of the estimated blur kernel and reducing  ...  Firstly, we estimate a motion vector between the current and the previous blurred frames, and introduce the estimated motion vector for deriving the motion-compensated frame with the previous restored  ...  Our improved blur kernel estimation method can improve more effective restored quality than the method proposed by Lee et al.  ... 
doi:10.3390/s18061774 pmid:29865162 pmcid:PMC6022012 fatcat:usbqbncmwjfphkid25lslzzcxi

Stereo Video Deblurring [article]

Anita Sellent, Carsten Rother, Stefan Roth
2016 arXiv   pre-print
Second, we exploit the estimated motion boundaries of the 3D scene flow to mitigate ringing artifacts using an iterative weighting scheme.  ...  We leverage 3D scene flow, which can be estimated robustly even under adverse conditions.  ...  In our approach, we exploit 3D scene flow in various ways and make the following contributions: (i) We show that 3D scene flow can improve video deblurring by providing more accurate motion estimates.  ... 
arXiv:1607.08421v1 fatcat:yzqtn4z6lrenbap6fa5mo32ajm

Invertible motion blur in video

Amit Agrawal, Yi Xu, Ramesh Raskar
2009 ACM SIGGRAPH 2009 papers on - SIGGRAPH '09  
estimation of moving parts, and non-degradation of the static parts of the scene.  ...  estimation of moving parts, and non-degradation of the static parts of the scene.  ...  For motion blur, coded exposure could be combined with our method at the expense of hardware modification to improve the SNR of the deblurred image.  ... 
doi:10.1145/1576246.1531401 fatcat:b5miyvpujre3dlzdog52rx55sy

Invertible motion blur in video

Amit Agrawal, Yi Xu, Ramesh Raskar
2009 ACM Transactions on Graphics  
estimation of moving parts, and non-degradation of the static parts of the scene.  ...  estimation of moving parts, and non-degradation of the static parts of the scene.  ...  For motion blur, coded exposure could be combined with our method at the expense of hardware modification to improve the SNR of the deblurred image.  ... 
doi:10.1145/1531326.1531401 fatcat:hfw3onivdresxhkq6gl5glwbta

Image/video deblurring using a hybrid camera

Yu-Wing Tai, Hao Du, Michael S. Brown, Stephen Lin
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
We demonstrate that our approach achieves superior results over existing work and can be extended to deblurring of moving objects. * This work was done while Yu-Wing Tai and Hao Du were visiting students  ...  Our work is inspired by Ben-Ezra and Nayar [3] who introduced the hybrid camera idea for correcting global motion blur for a single still image.  ...  In [3] , this relative motion is assumed to be constant throughout an image, and the globally invariant blur kernel is obtained through the integration of global motion vectors over a spline curve.  ... 
doi:10.1109/cvpr.2008.4587507 dblp:conf/cvpr/TaiDBL08 fatcat:xoeka7qnrfddhjx4ry6uuan62y

Pyramid Feature Alignment Network for Video Deblurring [article]

Leitian Tao, Zhenzhong Chen
2022 arXiv   pre-print
To better handle the challenges of complex and large motions, instead of aligning features at each scale separately, lower-scale motion information is used to guide the higher-scale motion estimation.  ...  We propose a Pyramid Feature Alignment Network (PFAN) for video deblurring.  ...  [35] presented blur-invariant motion estimation methods and a way to resolve motion estimation errors.  ... 
arXiv:2203.14556v1 fatcat:wivprlrlnvevdbzzfs4x63vd4u

A survey on image deblurring

A. Mahalakshmi, B. Shanthini
2016 2016 International Conference on Computer Communication and Informatics (ICCCI)  
After the process of deblurring, the improved quality of the image is capable to spot the specific exposure time.  ...  The blur removal due to camera shake and motion of the scene is been considered as a research topic in Image processing.  ...  Blind motion deblurring Accurate estimation of blur kernel and restore high quality clear image by multi frame blind deblurring approach. Linearized Bergmann iteration is also used.  ... 
doi:10.1109/iccci.2016.7479956 fatcat:dswfqan5e5d6jhm7wjw2f6yiha

Motion Deblurring with an Adaptive Network [article]

Kuldeep Purohit, A. N. Rajagopalan
2022 arXiv   pre-print
In this paper, we address the problem of dynamic scene deblurring in the presence of motion blur.  ...  and significant improvements in accuracy and speed, enabling almost real-time deblurring.  ...  Video Deblurring through Spatio-temporal recurrence A natural extension to single image deblurring is video deblurring.  ... 
arXiv:1903.11394v4 fatcat:jgsssxep6vfbnafshrg2x6ijke
« Previous Showing results 1 — 15 out of 1,265 results