Toward robust estimation of specular flow

Adato, Yair; Zickler, Todd; Ben-Shahar, Ohad

doi:10.5244/c.24.22

Cited by 10 publications

(31 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As already discussed recently in [3], the piecewise smoothness assumption used so often in the optical flow literature conflicts the nature of the specular flow. Indeed, while the former prefers smooth behavior and slow variations almost everywhere, specular singularities exhibits dramatic growth in flow magnitude combined with a sudden 180 degree orientation change.…”

Section: The Challenge Of Parabolic Singularitiesmentioning

confidence: 99%

“…Unfortunately, however, this is a poor choice. Indeed, as was argued recently [3], existing optical flow algorithms fail on specular flow data primarily because their regularization terms misrepresents the parabolic singularities and the significant variations in the flow magnitude. Alternatively, it was also suggested to avoid estimating the dense specular flow directly and instead to find a sparse set of corresponding reflection points in the image sequence which are far enough from parabolic singularities [17].…”

Section: Previous Workmentioning

confidence: 99%

“…(a) The setup: a specular surface is observed orthographically in a distant unknown illumination environment. (b) A real specular object with ground truth data from [3]. (c) A sample frame observed from the object.…”

Section: Previous Workmentioning

confidence: 99%

“…The most critical of which is the ability (of the lack thereof) to reconstruct specular flow reliably from image sequences. As argued in the past, specular flows are optical flows by definition and yet, they possess certain properties that prevent optical flow algorithms from estimating them reliably or reasonably [3]. It is well known, for example, that specular flows undergo unique singularities at (or near) the projection of parabolic lines, where reflected features are created and annihilated in pairs [2,12,23].…”

Section: Introductionmentioning

confidence: 99%

“…It is well known, for example, that specular flows undergo unique singularities at (or near) the projection of parabolic lines, where reflected features are created and annihilated in pairs [2,12,23]. In practice, this so called parabolic singularity [3] drives virtually all optical flow algorithms into global qualitative errors across the image plane. The same problem is revealed in related methods also, and is coped with by assuming no parabolic regions (e.g., [16,18]) or by explicit surface modeling (e.g., [15,17]).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Specular Flow and Shape in One Shot:

Adato

Ben-Shahar

2011

Procedings of the British Machine Vision Conference 2011

Self Cite

View full text Add to dashboard Cite

The reconstruction of specular shape from images is a very challenging task, especially when the illumination environment is unknown. In such cases, the problem becomes more tractable once the camera observes relative motion between the object and the environment, which induces a type of optical flow field that has become known as specular flow. Unfortunately, however, the estimation of specular flow from image sequences is even more challenging, putting in question the effectiveness of the shape from specular flow approach as a whole. Here we show that instead of the traditional (and somewhat futile) process of first estimating the specular flow and then using it for the recovery of specular shape, an approach that addresses these two inference problems simultaneously improves the estimation of both structures. We formulate the problem in a variational setting, we identify and address numerical issues unique to its application on specular flows, and we employ a polar representation of motion, all to result in the first ever practical method to compute specular shape from real image sequences under unknown illumination.

show abstract

Section: The Challenge Of Parabolic Singularitiesmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Specular Flow and Shape in One Shot:

Adato

Ben-Shahar

2011

Procedings of the British Machine Vision Conference 2011

Self Cite

View full text Add to dashboard Cite

show abstract

Detection and localization of specular surfaces using image motion cues

Yılmaz

Doerschner

2014

Machine Vision and Applications

View full text Add to dashboard Cite

Successful identification of specularities in an image can be crucial for an artificial vision system when extracting the semantic content of an image or while interacting with the environment. We developed an algorithm that relies on scale and rotation invariant feature extraction techniques and uses motion cues to detect and localize specular surfaces. Appearance change in feature vectors is used to quantify the appearance distortion on specular surfaces, which has previously been shown to be a powerful indicator for specularity (Doerschner et al. in Curr Biol, 2011). The algorithm combines epipolar deviations (Swaminathan et al. in Lect Notes Comput Sci 2350:508-523, 2002) and appearance distortion, and succeeds in localizing specular objects in computer-rendered and real scenes, across a wide range of camera motions and speeds, object sizes and shapes, and performs well under image noise and blur conditions. © 2014 Springer-Verlag Berlin Heidelberg

show abstract

A differential geometry approach to camera-independent image correspondence

Molnár

Eichhardt

2018

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Projective geometry is a standard mathematical tool for image-based 3D reconstruction. Most reconstruction methods establish pointwise image correspondences using projective geometry. We present an alternative approach based on differential geometry using oriented patches rather than points. Our approach assumes that the scene to be reconstructed is observed by any camera, existing or potential, that satisfies very general conditions, namely, the differentiability of the surface and the bijective projection functions. We show how the notions of the differential geometry such as diffeomorphism, pushforward and pullback are related to the reconstruction problem. A unified theory applicable to various 3D reconstruction problems is presented. Considering two views of the surface, we derive reconstruction equations for oriented patches and pose equations to determine the relative pose of the two cameras. Then we discuss the generalized epipolar geometry and derive the generalized epipolar constraint (compatibility equation) along the epipolar curves. Applying the proposed theory to the projective camera and assuming that affine mapping between small corresponding regions has been estimated, we obtain the minimal pose equation for the case when a fully calibrated camera is moved with its internal parameters unchanged. Equations for the projective epipolar constraints and the fundamental matrix are also derived. Finally, two important nonlinear camera types, the axial and the spherical, are examined.

show abstract

Toward robust estimation of specular flow

Cited by 10 publications

References 20 publications

Specular Flow and Shape in One Shot:

Specular Flow and Shape in One Shot:

Detection and localization of specular surfaces using image motion cues

A differential geometry approach to camera-independent image correspondence

Contact Info

Product

Resources

About