Super-resolution and Optical Flow reliability fields
نویسندگان
چکیده
Accurate optical flow estimation of motion fields is crucial for video super-resolution algorithms. Existing algorithms for optical flow calculation may produce erroneous motion fields on complex dynamic scenes with multiple moving, occluding non-rigid objects. In this paper we propose to use so called optical flow reliability weights in order to reduce impact of erroneous motion vector estimates on quality of super-resolution. We propose method for estimation of reliability weights which is based on structural analysis of motion vector fields. We present results on real video sequences and demonstrate the advantages of the proposed methods compared to conventional optical flow based super-resolution methods.
منابع مشابه
Super defocusing of light by optical sub-oscillations
The mathematical phenomenon of superoscillation, in which a spectrally bound function oscillates locally at a rate faster than its fastest Fourier component, has found use in both theoretical and applied areas of optical research. We show the existence of a complementary phenomenon we term sub-oscillation, in which a spectrally lower bound limited function oscillates locally at an arbitrarily l...
متن کاملSuper-Resolution Optical Flow
Existing approaches to super-resolution are not applicable to videos of faces because faces are non-planar, non-rigid, non-lambertian, and are subject to self occlusion. We present super-resolution optical ow as a solution to these problems. Super-resolution optical ow takes as input a conventional video stream, and simultaneously computes both optical ow and a super-resolution version of the e...
متن کاملPractical Super-Resolution from Dynamic Video Sequences
This paper introduces a practical approach for superresolution, the process of reconstructing a high-resolution image from the low-resolution input ones. The emphasis of our work is to super-resolve frames from dynamic video sequences which may contain significant object occlusion or scene changes. As the quality of super-resolved images highly relies on the correctness of image alignment betwe...
متن کاملEnd-to-End Learning of Video Super-Resolution with Motion Compensation
Learning approaches have shown great success in the task of super-resolving an image given a low resolution input. Video superresolution aims for exploiting additionally the information from multiple images. Typically, the images are related via optical flow and consecutive image warping. In this paper, we provide an end-to-end video superresolution network that, in contrast to previous works, ...
متن کاملImproving Super-Resolution Enhancement of Video by using Optical Flow
In the literature there has been much research into two methods of attacking the super-resolution problem: using optical flow-based techniques to align low-resolution images as samples of a target high-resolution image, and using learning-based techniques to estimate perceptuallyplausible high frequency components of a low-resolution image. Both of these approaches have been naturally extended ...
متن کامل