Highly Overparameterized Optical Flow Using PatchMatch Belief Propagation

Hornáček, Michael; Besse, Frederic; Kautz, Jan; Fitzgibbon, Andrew; Rother, Carsten

doi:10.1007/978-3-319-10578-9_15

Cited by 26 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sequential approach of [147] has proven to yield good results and computational performance compared to other discrete methods in [237]. It has been applied for optical flow estimation in [104,121,160,181]. It is also exploited for image matching involving large deformation models to cope with high computational complexity, as described in [216] or in the SIFT-Flow algorithm [166].…”

Section: Combinatorial Methodsmentioning

confidence: 99%

Optical flow modeling and computation: A survey

Fortun

Bouthémy

Kervrann

2015

Computer Vision and Image Understanding

369

182

View full text Add to dashboard Cite

a b s t r a c tOptical flow estimation is one of the oldest and still most active research domains in computer vision. In 35 years, many methodological concepts have been introduced and have progressively improved performances, while opening the way to new challenges. In the last decade, the growing interest in evaluation benchmarks has stimulated a great amount of work. In this paper, we propose a survey of optical flow estimation classifying the main principles elaborated during this evolution, with a particular concern given to recent developments. It is conceived as a tutorial organizing in a comprehensive framework current approaches and practices. We give insights on the motivations, interests and limitations of modeling and optimization techniques, and we highlight similarities between methods to allow for a clear understanding of their behavior.

show abstract

Section: Combinatorial Methodsmentioning

confidence: 99%

Optical flow modeling and computation: A survey

Fortun

Bouthémy

Kervrann

2015

Computer Vision and Image Understanding

369

182

View full text Add to dashboard Cite

show abstract

“…Optical Flow. PatchMatch has been shown to be effective in large displacement optical flows [10], [22], [5]. We simply replace the original PatchMatch in [5] to evaluate the effectiveness of our method.…”

Section: B Evaluation On Patchmatchmentioning

confidence: 98%

Fast Weighted Histograms for Bilateral Filtering and Nearest Neighbor Searching

Yang

Lau

et al. 2016

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

The locality sensitive histogram (LSH) injects spatial information into the local histogram in an efficient manner, and has been demonstrated to be very effective for visual tracking. In this paper, we explore the application of this efficient histogram in two important problems. We first extend the LSH to linear time bilateral filtering, and then propose a new type of histogram for efficiently computing edge-preserving nearest neighbor fields (NNF). While existing histogram-based bilateral filtering methods are the state-ofthe-art for efficient grayscale image processing, they are limited to box spatial filter kernels only. In our first application, we address this limitation by expressing the bilateral filter as a simple ratio of linear functions of the LSH, which is able to extend the box spatial kernel to an exponential kernel. The computational complexity of the proposed bilateral filter is linear in the number of image pixels. In our second application, we derive a new bilateral weighted histogram (BWH) for NNF. The new histogram maintains the efficiency of LSH, which allows approximate NNF to be computed independent of patch size. In addition, BWH takes into account both spatial and color information, and thus provides higher accuracy for histogram-based matching, especially around color edges.Index Terms-locality sensitive histograms, bilateral weighted histograms, bilateral filtering, nearest neighbor searching, edge-preserving smoothing.

show abstract

“…Local and global methods may involve parametric motion models [12,29,30,39,45,53,54,56,63,77,87]. The most frequently adopted ones are polynomial motion models such as translation, affine, quadratic, but other models can be investigated as well [45].…”

Section: Related Workmentioning

confidence: 99%

“…The most frequently adopted ones are polynomial motion models such as translation, affine, quadratic, but other models can be investigated as well [45]. When attached to local optimization, the parametric motion models are estimated on local regions usually defined as square patches centered on each pixel [12,54], possibly with an adaptation of the patch size [55,70], or its position [49].…”

Section: Related Workmentioning

confidence: 99%

A Variational Aggregation Framework for Patch-Based Optical Flow Estimation

2016

View full text Add to dashboard Cite

We propose a variational aggregation method for optical flow estimation. It consists of a two-step framework, first estimating a collection of parametric motion models to generate motion candidates, and then reconstructing a global dense motion field. The aggregation step is designed as a motion reconstruction problem from spatially varying sets of motion candidates given by parametric motion models. Our method is designed to capture large displacements in a variational framework without requiring any coarse-tofine strategy. We handle occlusion with a motion inpainting approach in the candidates computation step. By performing parametric motion estimation, we combine the robustness to noise of local parametric methods with the accuracy yielded by global regularization. We demonstrate the performance of our aggregation approach by comparing it to standard variational methods and a discrete aggregation approach on the Middlebury and MPI Sintel datasets.

show abstract

Highly Overparameterized Optical Flow Using PatchMatch Belief Propagation

Cited by 26 publications

References 25 publications

Optical flow modeling and computation: A survey

Optical flow modeling and computation: A survey

Fast Weighted Histograms for Bilateral Filtering and Nearest Neighbor Searching

A Variational Aggregation Framework for Patch-Based Optical Flow Estimation

Contact Info

Product

Resources

About