Large displacement optical flow computation withoutwarping

Steinbrücker, Frank; Pock, Thomas; Cremers, Daniel

doi:10.1109/iccv.2009.5459364

Cited by 102 publications

(80 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The functions u and v are coupled by the term 1 2θ (u − v) 2 . This decoupling approach allows for an efficient GPU implementation and has been used in many related problems [22,17,14].…”

Section: Minimizationmentioning

confidence: 99%

Dense 3D Reconstruction with a Hand-Held Camera

Ummenhofer

Brox

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper we present a method for dense 3D reconstruction from videos where object silhouettes are hard to retrieve. We introduce a close coupling between sparse bundle adjustment and dense multiview reconstruction, which includes surface constraints by the sparse point cloud and an implicit loop closing via the dense surface. The surface is computed in a volumetric framework and guarantees a dense surface without holes. We demonstrate the flexibility of the approach on indoor and outdoor scenes recorded with a commodity hand-held camera.

show abstract

Section: Minimizationmentioning

confidence: 99%

Dense 3D Reconstruction with a Hand-Held Camera

Ummenhofer

Brox

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…As stated in (22), the space H div (R 2 ) corresponds to the curl of H 1 (R 2 ) scalar potential. Then, taking the curl of any multiresolution analysis of H 1 (R 2 ) will provide a multiresolution analysis of H div (R 2 ).…”

Section: Divergence-free Wavelet Basismentioning

confidence: 99%

“…Dealing with non-linearities and the multi-scale structure of motion is particularly challenging for the estimation of deformation fields generated by physical processes. Gaussian multiresolution frameworks [1] or combined integrated/variational formulations [22] have been proposed to circumvent non-linearity and achieve long range displacement estimation from consecutive images. However, the former solutions suffer from a non nested minimization formulation that may impact estimation accuracy, while the latter provide poor results for non-textured images such as images visualizing the transport of a passive scalar.…”

mentioning

confidence: 99%

Divergence-Free Wavelets and High Order Regularization

et al. 2012

View full text Add to dashboard Cite

Expanding on a wavelet basis the solution of an inverse problem provides several advantages. First of all, wavelet bases yield a natural and efficient multiresolution analysis which allows defining clear optimization strategies on nested subspaces of the solution space. Besides, the continuous representation of the solution with wavelets enables analytical calculation of regularization integrals over the spatial domain. By choosing differentiable wavelets, accurate high-order derivative regularizers can be efficiently designed via the basis's mass and stiffness matrices. More importantly, differential constraints on vector solutions, such as the divergencefree constraint in physics, can be nicely handled with biorthogonal wavelet bases. This paper illustrates these advantages in the particular case of fluid flow motion estimation. Numerical results on synthetic and real images of incompressible turbulence show that divergencefree wavelets and high-order regularizers are particularly relevant in this context.

show abstract

“…Traditional methods handle small motion while recent development in this field begins to tackle the more challenging large-displacement estimation problem [1][2][3][4][5]. These effective methods, however, still do not consider large and non-uniform scale variation, which is ubiquitous when images are sparsely captured or objects quickly move towards or away from the camera.…”

Section: Introductionmentioning

confidence: 99%

Scale Invariant Optical Flow

Liu

Dai

Jia

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

Abstract. Scale variation commonly arises in images/videos, which cannot be naturally dealt with by optical flow. Invariant feature matching, on the contrary, provides sparse matching and could fail for regions without conspicuous structures. We aim to establish dense correspondence between frames containing objects in different scales and contribute a new framework taking pixel-wise scales into consideration in optical flow estimation. We propose an effective numerical scheme, which iteratively optimizes discrete scale variables and continuous flow ones. This scheme notably expands the practicality of optical flow in natural scenes containing various types of object motion.

show abstract

Large displacement optical flow computation withoutwarping

Abstract: We

Cited by 102 publications

References 11 publications

Dense 3D Reconstruction with a Hand-Held Camera

Dense 3D Reconstruction with a Hand-Held Camera

Divergence-Free Wavelets and High Order Regularization

Scale Invariant Optical Flow

Contact Info

Product

Resources

About