Symmetric Optical Flow

Álvarez, Luis; Castaño, C. A.; García, Miguel Ángel; Krissian, Karl; Mazorra, Luis; Salgado, Agustín; Sánchez, Javier

doi:10.1007/978-3-540-75867-9_85

Cited by 11 publications

(12 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We then compute the spatial derivatives of the first image, compute the average of these and the corresponding warped derivatives of the second image (cf. Álvarez et al 2007;Horn 1986), and use these in place of…”

Section: Baseline Methodsmentioning

confidence: 99%

A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them

2013

View full text Add to dashboard Cite

The accuracy of optical flow estimation algorithms has been improving steadily as evidenced by results on the Middlebury optical flow benchmark. The typical formulation, however, has changed little since the work of Horn and Schunck. We attempt to uncover what has made recent advances possible through a thorough analysis of how the objective function, the optimization method, and modern implementation practices influence accuracy. We discover that "classical" flow formulations perform surprisingly well when combined with modern optimization and implementation techniques. One key implementation detail is the median filtering of intermediate flow fields during optimization. While this improves the robustness of classical methods it actually leads to higher energy solutions, meaning that these methods are not optimizing the original objective function. To understand the principles behind this phenomenon, we derive a new objective function that formalizes the median filtering heuristic. This objective function includes a non-local smoothness term that robustly integrates flow estimates over large spatial neighborhoods. By modifying this Portions of this work were performed when DS and MJB were at Brown University. new term to include information about flow and image boundaries we develop a method that can better preserve motion details. To take advantage of the trend towards video in widescreen format, we further introduce an asymmetric pyramid downsampling scheme that enables the estimation of longer range horizontal motions. The methods are evaluated on the Middlebury, MPI Sintel, and KITTI datasets using the same parameter settings.

show abstract

Section: Baseline Methodsmentioning

confidence: 99%

A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them

2013

View full text Add to dashboard Cite

show abstract

“…We propose to include a truly symmetric flow estimate which is calculated directly using the pixel positions of the unknown frame I1 /2 , to complement the two asymmetric flows. This flow v s is calculated using the reparametrization of (3) first suggested by Alvarez et al 18 , and recently analyzed in a frame interpolation setup by Rakêt et al 2 i.e. replacing the data fidelity term in (3) by…”

Section: Frame Interpolation Algorithm and Resultsmentioning

confidence: 99%

Exploiting the error-correcting capabilities of low-density parity check codes in distributed video coding using optical flow

et al. 2012

View full text Add to dashboard Cite

We consider Distributed Video Coding (DVC) in presence of communication errors. First, we present DVC side information generation based on a new method of optical flow driven frame interpolation, where a highly optimized TV-L 1 algorithm is used for the flow calculations and combine three flows. Thereafter methods for exploiting the error-correcting capabilities of the LDPCA code in DVC are investigated. The proposed frame interpolation includes a symmetric flow constraint to the standard forward-backward frame interpolation scheme, which improves quality and handling of large motion. The three flows are combined in one solution. The proposed frame interpolation method consistently outperforms an overlapped block motion compensation scheme and a previous TV-L 1 optical flow frame interpolation method with an average PSNR improvement of 1.3 dB and 2.3 dB respectively. For a GOP size of 2, an average bitrate saving of more than 40% is achieved compared to DISCOVER on Wyner-Ziv frames. In addition we also exploit and investigate the internal error-correcting capabilities of the LDPCA code in order to make it more robust to errors. We investigate how to achieve this goal by only modifying the decoding. One of approaches is to use bit flipping; alternatively one can modify the parity check matrix of the LDPCA. Different schemes known from LDPC codes are considered and evaluated in the LDPCA setting. Results show that the performance depend heavily on the type of channel used and on the quality of the Side Information.

show abstract

“…A similar idea was applied to the optical flow problem by Alvarez et al [2], who imposed an additional consistency term. Later that same year Alvarez et al [3] proposed a reparametrization similar to the one derived in this paper in order to avoid a reference frame, and thereby increase flow consistency. However, they did not use the obtained symmetric flow directly, but interpolated flow values at pixel position of a reference image in order to obtain a flow comparable to the standard asymmetric flow.…”

Section: Introductionmentioning

confidence: 98%

“…Apart from being algorithmically different, the difference between the justification given in this paper and the justifications of Alvarez et al [3] and Chen [4] is that we have chosen the symmetric data fidelity term because it explicitly models the standard interpolation assumption, rather than improves some notion of consistency or better handles large displacements. In turn this also means that we use the estimated flows directly on the unknown frame, and thereby avoid problems of temporal warping.…”

Section: Introductionmentioning

confidence: 99%

Motion Compensated Frame Interpolation with a Symmetric Optical Flow Constraint

Rakêt

Roholm

Bruhn

et al. 2012

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. We consider the problem of interpolating frames in an image sequence. For this purpose accurate motion estimation can be very helpful. We propose to move the motion estimation from the surrounding frames directly to the unknown frame by parametrizing the optical flow objective function such that the interpolation assumption is directly modeled. This reparametrization is a powerful trick that results in a number of appealing properties, in particular the motion estimation becomes more robust to noise and large displacements, and the computational workload is more than halved compared to usual bidirectional methods. The proposed reparametrization is generic and can be applied to almost every existing algorithm. In this paper we illustrate its advantages by considering the classic TV-L 1 optical flow algorithm as a prototype. We demonstrate that this widely used method can produce results that are competitive with current state-of-the-art methods. Finally we show that the scheme can be implemented on graphics hardware such that it becomes possible to double the frame rate of 640 × 480 video footage at 30 fps, i.e. to perform frame doubling in realtime.

show abstract

Symmetric Optical Flow

Cited by 11 publications

References 5 publications

A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them

A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them

Exploiting the error-correcting capabilities of low-density parity check codes in distributed video coding using optical flow

Motion Compensated Frame Interpolation with a Symmetric Optical Flow Constraint

Contact Info

Product

Resources

About