Consistent Wce Video Frame Interpolation Based On Endoscopy Image Motion Estimation

2021 ◽  
Author(s):  
Bing Jiang ◽  
Yuyao Zhang ◽  
Minye Wu ◽  
Ji Li ◽  
Jingyi Yu
Keyword(s):  
Motion Estimation ◽  
Image Motion ◽  
Video Frame ◽  
Frame Interpolation

Fine-Grained Motion Estimation for Video Frame Interpolation

2020 ◽  
pp. 1-11
Author(s):  
Bo Yan ◽  
Weimin Tan ◽  
Chuming Lin ◽  
Liquan Shen
Keyword(s):  
Motion Estimation ◽  
Video Frame ◽  
Frame Interpolation ◽  
Fine Grained

scholarly journals Video Frame Interpolation via Deformable Separable Convolution

2020 ◽  
Vol 34 (07) ◽  
pp. 10607-10614 ◽  
Author(s):  
Xianhang Cheng ◽  
Zhenzhong Chen
Keyword(s):  
State Of The Art ◽  
Video Frame ◽  
Kernel Size ◽  
Frame Interpolation ◽  
Interpolation Methods ◽  
Video Frames ◽  
Convolution Process ◽  
Strong Performance ◽  
Existing Frames ◽  
Better Than

Learning to synthesize non-existing frames from the original consecutive video frames is a challenging task. Recent kernel-based interpolation methods predict pixels with a single convolution process to replace the dependency of optical flow. However, when scene motion is larger than the pre-defined kernel size, these methods yield poor results even though they take thousands of neighboring pixels into account. To solve this problem in this paper, we propose to use deformable separable convolution (DSepConv) to adaptively estimate kernels, offsets and masks to allow the network to obtain information with much fewer but more relevant pixels. In addition, we show that the kernel-based methods and conventional flow-based methods are specific instances of the proposed DSepConv. Experimental results demonstrate that our method significantly outperforms the other kernel-based interpolation methods and shows strong performance on par or even better than the state-of-the-art algorithms both qualitatively and quantitatively.

An Improved Object-Based Video Segmentation Method

2012 ◽  
Vol 220-223 ◽  
pp. 2445-2449
Author(s):  
Wen Dan Xu ◽  
Xin Quan Lai ◽  
Dong Lai Xu
Keyword(s):  
Motion Estimation ◽  
Video Compression ◽  
High Performance ◽  
Video Segmentation ◽  
Error Function ◽  
Least Square ◽  
Video Frame ◽  
Merging Process ◽  
Initial Segmentation ◽  
Two Stages

This paper presents an improved video segmentation scheme, which consists of two stages: initial segmentation and motion estimation. In the initial segmentation, the watershed transformation followed by a region adjacency graph guided region merging process is used to partition the first video frame into spatial homogenous regions. Then the motion of changed region is estimated. Based on the highly efficient quadratic motion model, the motion estimation is undertaken using Gauss-Newton Levenberg-Marquardt method to minimize the least-square error function. Experimental results show the proposed scheme provides high performance in terms of segmentation accuracy and video compression ratio.

Sign in / Sign up

Export Citation Format

Share Document