Non-parametric local transforms for computing visual correspondence

Zabih, Ramin; Woodfill, John

doi:10.1007/bfb0028345

Cited by 1,471 publications

(970 citation statements)

References 10 publications

Supporting

Mentioning

957

Contrasting

Unclassified

Order By: Relevance

“…In 1994, Zabih and Woodfill have proposed the so-called census transform [1]. It computes for every pixel a binary string (census signature) by comparing its grey value with the grey values in its neighbourhood.…”

Section: Introductionmentioning

confidence: 99%

Why Is the Census Transform Good for Robust Optic Flow Computation?

Hafner

Demetz

Weickert

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The census transform is becoming increasingly popular in the context of optic flow computation in image sequences. Since it is invariant under monotonically increasing grey value transformations, it forms the basis of an illumination-robust constancy assumption. However, its underlying mathematical concepts have not been studied so far. The goal of our paper is to provide this missing theoretical foundation. We study the continuous limit of the inherently discrete census transform and embed it into a variational setting. Our analysis shows two surprising results: The census-based technique enforces matchings of extrema, and it induces an anisotropy in the data term by acting along level lines. Last but not least, we establish links to the widely-used gradient constancy assumption and present experiments that confirm our findings.

show abstract

Section: Introductionmentioning

confidence: 99%

Why Is the Census Transform Good for Robust Optic Flow Computation?

Hafner

Demetz

Weickert

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The census transform is a non-parametric local transform, which was first proposed by Zabih and Woodfill [16]. It transforms an image into the binary image which is invariant to illumination and viewpoint changes as mentioned by Furukawa et al [17].…”

Section: Initial Depth Estimation Using Census Transformmentioning

confidence: 99%

Depth Map Estimation Using Census Transform for Light Field Cameras

Tomioka

Mishiba

Oyamada

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYDepth estimation for a lense-array type light field camera is a challenging problem because of the sensor noise and the radiometric distortion which is a global brightness change among sub-aperture images caused by a vignetting effect of the micro-lenses. We propose a depth map estimation method which has robustness against sensor noise and radiometric distortion. Our method first binarizes sub-aperture images by applying the census transform. Next, the binarized images are matched by computing the majority operations between corresponding bits and summing up the Hamming distance. An initial depth obtained by matching has ambiguity caused by extremely short baselines among sub-aperture images. After an initial depth estimation process, we refine the result with following refinement steps. Our refinement steps first approximate the initial depth as a set of depth planes. Next, we optimize the result of plane fitting with an edge-preserving smoothness term. Experiments show that our method outperforms the conventional methods.

show abstract

“…The census cost is based on the census transform as introduced by Zabi and Woodfill [21]. A binary signature vector is assigned to each pixel position p = (i, j) of the base and match image.…”

Section: Algorithm Configurationmentioning

confidence: 99%

Hierarchical Scan-Line Dynamic Programming for Optical Flow Using Semi-Global Matching

Hermann

Klette

2013

Computer Vision - ACCV 2012 Workshops

View full text Add to dashboard Cite

Abstract. Dense and robust optical flow estimation is still a major challenge in low-level computer vision. In recent years, mainly variational methods contributed to the progress in this field. One reason for their success is their suitability to be embedded into hierarchical schemes, which makes them capable of handling large pixel displacements. Matching-based regularization techniques, like dynamic programming or belief propagation concepts, can also lead to accurate optical flow fields. However, results are limited to short-or mid-scale optical flow vectors, because these techniques are usually not coupled with coarse-to-fine strategies. This paper introduces fSGM, a novel algorithm that is based on scan-line dynamic programming. It uses the cost integration strategy of semi-global matching, a concept well known in the area of stereo matching. The major novelty of fSGM is that it embeds the scan-line dynamic programming approach into a hierarchical scheme, which allows it to handle large pixel displacements with an accuracy comparable to variational methods. We prove the exceptional performance of fSGM by comparing it to current state-of-the-art methods on the KITTI Vision Benchmark Suite.

show abstract

Non-parametric local transforms for computing visual correspondence

Cited by 1,471 publications

References 10 publications

Why Is the Census Transform Good for Robust Optic Flow Computation?

Why Is the Census Transform Good for Robust Optic Flow Computation?

Depth Map Estimation Using Census Transform for Light Field Cameras

Hierarchical Scan-Line Dynamic Programming for Optical Flow Using Semi-Global Matching

Contact Info

Product

Resources

About