Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions

By David Gallup, Jan-Michael Frahm, Philippos Mordohai, Qingxiong Yang, Marc Pollefeys. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

354 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ca2d5bb3c771d9286e9b2cef3f86eb5553cc4f6f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Real-Time Visibility-Based Fusion of Depth Maps (2007, methodology): “The depth maps are computed using the plane-sweeping technique described in [5].”
Semi-global Stereo Matching with Surface Orientation Priors (2017, neutral): “Plane-sweep stereo with a preferred plane orientation was proposed by Collins [11], and subsequently extended to multiple plane orientations, Manhattan-world scenes, and piece-wise planar scenes [18, 17, 43, 30].”
PatchMatch Stereo - Stereo Matching with Slanted Support Windows (2011, background): “2 Instead of adding additional fronto-parallel planes to the label space, one can add slanted ones [5].”
Multi-View Stereo: A Tutorial (2015, methodology): “11: Streetside reconstructions by plane sweeping stereo algorithm by Gallup, Frahm, Mordohai, Yang, and Pollefeys [76].”
Massively Parallel Multiview Stereopsis by Surface Normal Diffusion (2015, methodology): “[14] have proposed to align the plane to the dominant orientation in the scene.”
Pixelwise View Selection for Unstructured Multi-View Stereo (2016, background): “[59] map between the reference and source images using frontoparallel homographies leading to artifacts for oblique structures [17].”
Detailed Real-Time Urban 3D Reconstruction from Video (2007, methodology): “The next step of our system is to compute the depth of the scene using stereo [22].”
A Survey of Urban Reconstruction (2013, methodology): “Plane sweeping has been successfully utilized for the recovery of dense structure and was consecutively extended to utilize programmable graphics hardware [YP03] and multiple sweeping directions [GFM ∗ 07].”
Towards Internet-scale multi-view stereo (2010, methodology): “In particular, several algorithms operate by solving for a depth map for each image, using a local neighborhood of nearby images, and then merge the resulting reconstructions [11, 12, 18, 19].”
Consistent Depth Maps Recovery from a Video Sequence (2009, neutral): “E-mail: {leojia, ttwong}@cse.cuhk.edu.hk. Manuscript received 8 Aug. 2008; revised 3 Jan. 2009; accepted 19 Feb. 2009; published online 24 Feb. 2009.”
Real-Time Direct Dense Matching on Fisheye Images Using Plane-Sweeping Stereo (2014, methodology): “The only requirement we need for the fisheye model is that both projection and unprojection can be done efficiently.”
REMODE: Probabilistic, monocular dense reconstruction in real time (2014, background): “If, on one hand, estimating the depth independently for every pixel leads to efficient, parallel implementations, on the other hand the authors of [10], [11], [12] argued that, similar to other computer vision problems, such as image de-noising [13] and optical flow estimation [14], a smoothing step”
Robust Probabilistic Occupancy Grid Estimation from Positive and Negative Distance Fields (2012, methodology): “Raw depth maps are computed from a set of calibrated images using plane-sweeping stereo implemented on the GPU similar to [8] with normalized cross-correlation (NCC) as the similarity function.”
Patches, Planes and Probabilities: A Non-Local Prior for Volumetric 3D Reconstruction (2016, methodology): “The only remaining unknown is the rotation around the Z axis, which we compute as the entropy minimizer of the point cloud projections onto canonical orthogonal X and Y planes (see [16] for details).”