A space-sweep approach to true multi-image matching

Collins, Robert T.

doi:10.1109/cvpr.1996.517097

Cited by 492 publications

(306 citation statements)

References 6 publications

Supporting

Mentioning

304

Contrasting

Unclassified

Order By: Relevance

“…In practice, we would like to use more than two images in order to obtain a more accurate and robust correspondence [5], [20]. In this section, we study whether the epipolar geometry is sufficiently close to a horizontal epipolar geometry so that conventional multiimage stereo matching algorithms such as EPI analysis [4], SSSD [20], and plane sweep [5], [12], [32] can be used.…”

Section: Small Disparity and Angle Approximationsmentioning

confidence: 99%

“…In this section, we study whether the epipolar geometry is sufficiently close to a horizontal epipolar geometry so that conventional multiimage stereo matching algorithms such as EPI analysis [4], SSSD [20], and plane sweep [5], [12], [32] can be used.…”

Section: Small Disparity and Angle Approximationsmentioning

confidence: 99%

“…Plane-sweep and space coloring/carving stereo algorithms have recently become popular because they support true multi-image matching [5], enable reasoning about occlusion relationships [12], [14], [15], [27], [32], and are more efficient than traditional correlation-based formulations [10]. Traditional stereo matching algorithms pick a window around each pixel in a reference image and then find corresponding windows in other images at every candidate disparity (searching along an epipolar line).…”

Section: Cylinder Sweep Stereomentioning

confidence: 99%

“…Traditional stereo matching algorithms pick a window around each pixel in a reference image and then find corresponding windows in other images at every candidate disparity (searching along an epipolar line). Plane sweep algorithms consider each candidate disparity as defining a plane in space and project all images to be matched onto that plane, using a planar perspective transform (homography) [1], [5], [32]. A perpixel fitness metric (e.g., the variance of the corresponding collection of pixels) is first computed and then aggregated spatially using an efficient convolution algorithm (e.g., a moving average box filter) or some other techniques [25], [26].…”

Section: Cylinder Sweep Stereomentioning

confidence: 99%

“…On the other hand, multibaseline stereo using several images has produced better depth maps by averaging out noise and reducing ambiguities [12], [20]. Space-sweep approaches, which project multiple images onto a series of imaging surfaces (usually planes), also explore significant data redundancy for better reconstruction (e.g., [5], [15], [27], [32]). Space-sweep approaches in general need to discretize the scene volume and, therefore, sampling strategies ( [3], [33]).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Stereo reconstruction from multiperspective panoramas

Shum

Tang

et al. 2004

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

Abstract-A new approach to computing a panoramic (360 degrees) depth map is presented in this paper. Our approach uses a large collection of images taken by a camera whose motion has been constrained to planar concentric circles. We resample regular perspective images to produce a set of multiperspective panoramas and then compute depth maps directly from these resampled panoramas. Our panoramas sample uniformly in three dimensions: rotation angle, inverse radial distance, and vertical elevation. The use of multiperspective panoramas eliminates the limited overlap present in the original input images and, thus, problems as in conventional multibaseline stereo can be avoided. Our approach differs from stereo matching of single-perspective panoramic images taken from different locations, where the epipolar constraints are sine curves. For our multiperspective panoramas, the epipolar geometry, to the first order approximation, consists of horizontal lines. Therefore, any traditional stereo algorithm can be applied to multiperspective panoramas with little modification. In this paper, we describe two reconstruction algorithms. The first is a cylinder sweep algorithm that uses a small number of resampled multiperspective panoramas to obtain dense 3D reconstruction. The second algorithm, in contrast, uses a large number of multiperspective panoramas and takes advantage of the approximate horizontal epipolar geometry inherent in multiperspective panoramas. It comprises a novel and efficient 1D multibaseline matching technique, followed by tensor voting to extract the depth surface. Experiments show that our algorithms are capable of producing comparable high quality depth maps which can be used for applications such as view interpolation.

show abstract

Section: Small Disparity and Angle Approximationsmentioning

confidence: 99%

Section: Small Disparity and Angle Approximationsmentioning

confidence: 99%

Section: Cylinder Sweep Stereomentioning

confidence: 99%

Section: Cylinder Sweep Stereomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Stereo reconstruction from multiperspective panoramas

Shum

Tang

et al. 2004

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

show abstract

Multi‐Event‐Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion

Ghosh

Gallego

2022

Advanced Intelligent Systems

View full text Add to dashboard Cite

Event cameras are bio‐inspired sensors that offer advantages over traditional cameras. They operate asynchronously, sampling the scene at microsecond resolution and producing a stream of brightness changes. This unconventional output has sparked novel computer vision methods to unlock the camera's potential. Here, the problem of event‐based stereo 3D reconstruction for SLAM is considered. Most event‐based stereo methods attempt to exploit the high temporal resolution of the camera and the simultaneity of events across cameras to establish matches and estimate depth. By contrast, this work investigates how to estimate depth without explicit data association by fusing disparity space images (DSIs) originated in efficient monocular methods. Fusion theory is developed and applied to design multi‐camera 3D reconstruction algorithms that produce state‐of‐the‐art results, as confirmed by comparisons with four baseline methods and tests on a variety of available datasets.

show abstract

Live accurate and dense reconstruction from a handheld camera

Chen

Hao

Cai

et al. 2013

Computer Animation & Virtual

View full text Add to dashboard Cite

We present a method to make an accurate and dense reconstruction from the input of video captured by a free moving handheld camera in real time. By the method firstly, the positions of the camera and sparse 3D points are estimated by simultaneous localization mapping. Then the depth maps of selected reference frames are computed from corresponding camera bundles. Lastly a novel linear algorithm is also proposed to integrate all the depth maps into dense meshes partially. The main contributions of this paper are in the following points: the reference frames and corresponding camera bundles are able to be selected automatically, then accurate and smooth depth maps are generated in real time, and the depth maps are merged into a dense mesh by using a linear algorithm based on the error clouds optimization. Our algorithm is implemented on dual CPU and graphics processing unit in a parallel framework for improving the performance. Copyright © 2013 John Wiley & Sons, Ltd.

show abstract

A space-sweep approach to true multi-image matching

Cited by 492 publications

References 6 publications

Stereo reconstruction from multiperspective panoramas

Stereo reconstruction from multiperspective panoramas

Multi‐Event‐Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion

Live accurate and dense reconstruction from a handheld camera

Contact Info

Product

Resources

About