Computing visual correspondence with occlusions using graph cuts

Kolmogorov, Vladimir; Zabih, Ramin

doi:10.1109/iccv.2001.937668

Cited by 876 publications

(738 citation statements)

References 16 publications

(33 reference statements)

Supporting

Mentioning

708

Contrasting

Unclassified

Order By: Relevance

“…When the feature values of the two images are close and temporally smooth, this displacement can be formulated as a continuous variable and the estimation problem is often reduced to solving PDE's using Euler-Lagrange [11], [29]. When the feature values are different, or other information such as occlusion needs to be taken into account, one can use belief propagation [22], [49] and graph cuts [9], [31] to optimize objective functions formulated on Markov random fields. The recent studies show that optimization tools such as belief propagation, tree-reweighted belief propagation and graph cuts can achieve very good local optimum for these optimization problems [52].…”

Section: Related Workmentioning

confidence: 99%

SIFT Flow: Dense Correspondence Across Scenes and Its Applications

Liu¹,

Yuen²,

Torralba³

2016

Dense Image Correspondences for Computer Vision

458

855

View full text Add to dashboard Cite

Abstract-While image alignment has been studied in different areas of computer vision for decades, aligning images depicting different scenes remains a challenging problem. Analogous to optical flow where an image is aligned to its temporally adjacent frame, we propose SIFT flow, a method to align an image to its nearest neighbors in a large image corpus containing a variety of scenes. The SIFT flow algorithm consists of matching densely sampled, pixel-wise SIFT features between two images, while preserving spatial discontinuities. The SIFT features allow robust matching across different scene/object appearances, whereas the discontinuitypreserving spatial model allows matching of objects located at different parts of the scene. Experiments show that the proposed approach robustly aligns complex scene pairs containing significant spatial differences. Based on SIFT flow, we propose an alignmentbased large database framework for image analysis and synthesis, where image information is transferred from the nearest neighbors to a query image according to the dense scene correspondence. This framework is demonstrated through concrete applications, such as motion field prediction from a single image, motion synthesis via object transfer, satellite image registration and face recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

SIFT Flow: Dense Correspondence Across Scenes and Its Applications

Liu¹,

Yuen²,

Torralba³

2016

Dense Image Correspondences for Computer Vision

458

855

View full text Add to dashboard Cite

show abstract

“…Some existing stereo match algorithms can achieve good results on a single pair of stereo frames [1,4,5,6]. They formulate the problem within an energy minimization framework and the energy is then optimized using one of the popular optimization methods such as graph cuts [7,8] However, these methods are not sufficient for depth estimation on a stereo image sequence, without considering the temporal consistency between adjacent frames. Previous research shows that better and more consistent disparity maps can be achieved by incorporating temporal constraints into stereo models [16,17,18,19,20,21].…”

Section: Introductionmentioning

confidence: 99%

Disparity Estimation in Stereo Sequences using Scene Flow

Liu

Philomin

2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

This paper presents a method for estimating disparity images from a stereo image sequence. While many existing stereo algorithms work well on a single pair of stereo images, it is not sufficient to simply apply them to temporal frames independently without considering the temporal consistency between adjacent frames. Our method integrates the state-of-the-art stereo algorithm with the scene flow concept in order to capture the temporal correspondences. It computes the dense disparity images and scene flow in a practical and unified process: the disparity is initialized by a hybrid stereo approach which employs the over-segmentation based stereo and pixelwise iterative stereo; then the scene flow, estimated via a variational approach, is used to predict the disparity image and to compute its confidence map for the next frame. The prediction is modeled as a prior probability distribution and is built into an energy function defined for stereo matching on the next frame. The disparity can be estimated by minimizing this energy function. Experimental results show that the algorithm is able to estimate the disparity images in an accurate and temporally consistent fashion.

show abstract

“…Early approaches [12,2] used local and window-based methods, and employed a local "winner-takes-all" (WTA) strategy in depth estimation at each pixel. Later on, several global methods [10,19,8] were proposed, which formulate the depth estimation as an energy-minimization problem, and commonly apply graph cuts or belief propagation to solve it. It is known that loopy belief propagation and multi-label graph cuts do not guarantee global optimal solutions in energy minimization, especially when the matching costs are not distinctive in textureless areas.…”

Section: Related Workmentioning

confidence: 99%

Recovering consistent video depth maps via bundle optimization

Jia

Wong

Bao³

2008

2008 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

input sequence output video depth maps Figure 1. High-quality depth reconstruction from the video sequence "Road" containing complex occlusions. Left: An input video sequence taken by a moving camera. Right: Video depth maps automatically computed by our method. The thin posts of the traffic sign and street lamp, as well as the road with graduate depth change, are accurately constructed in the recovered depth maps. Abstract This paper presents a novel method for reconstructing high-quality video depth maps. A bundle optimization model is proposed to address the key issues, including im

show abstract

Computing visual correspondence with occlusions using graph cuts

Abstract: Several new algorithms for visual correspondence based on graph cuts [7,14,17]

Cited by 876 publications

References 16 publications

SIFT Flow: Dense Correspondence Across Scenes and Its Applications

SIFT Flow: Dense Correspondence Across Scenes and Its Applications

Disparity Estimation in Stereo Sequences using Scene Flow

Recovering consistent video depth maps via bundle optimization

Contact Info

Product

Resources

About