Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Stereo Processing by Semi-global Matching and Mutual Information

How researchers see this paper

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

Citations in the corpus

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation (2015, methodology): “Also on the other datasets DispNet performs well and outperforms both SGM and MC-CNN.”
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics (2017, methodology): “Depth images are also provided, labelled using SGM [22], which we treat as pseudo ground truth.”
Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches (2015, methodology): “Following Hirschm¨uller (2008), we deﬁne an energy function E ( D ) that depends on the disparity image D : where 1 {·} denotes the indicator function.”
Massively Parallel Multiview Stereopsis by Surface Normal Diffusion (2015, unknown): “[11, 18, 27] or variational inference [31].”
Robust stereo matching with surface normal prediction (2017, methodology): “Semi-Global Matching (SGM) [17] both considers pixelwise matching and global smoothness constraints.”
A Comprehensive Automated 3D Approach for Building Extraction, Reconstruction, and Regularization from Airborne Laser Scanning Point Clouds (2008, unknown): “A Digital Surface Model (DSM) derived from point clouds acquired by Airborne Laser Scanning (ALS) [5] or stereophotogrammetry [6, 7] already represents buildings.”
Fast Disparity Estimation Using Dense Networks (2018, background): “Also shown are the results for SGM and MC-CNN-fast to established the baselines.”
Piecewise Rigid Scene Flow (2013, methodology): “As baselines we use our implementations of three methods: L1-regularized 3D scene flow (LSF, [3]); locally rigid 3D scene flow (Rig, [22]); and independently derived 2D stereo (semi-global matching [9]) and optical flow (census data term, total generalized variation [25] regularization), indicated b”
Comparing ALS and Image-Based Point Cloud Metrics and Modelled Forest Inventory Attributes in a Complex Coastal Forest Environment (2015, methodology): “We used the semi-global matching (SGM) algorithm [25] to generate dense image-based point clouds, implemented in the Remote Sensing Software Package Graz (RSG version 7.”
MicMac – a free, open-source solution for photogrammetry (2017, methodology): “Today the golden standard method for producing dense 3D models from images is the semi-global matching [6].”
DepthCN: Vehicle detection using 3D-LIDAR and ConvNet (2017, methodology): “Disparity maps are computed from each pair of left-right images of stereo cameras employing the Semi-Global Matching (SGM) [15] method.”
On the Uncertainty of Self-Supervised Monocular Depth Estimation (2020, methodology): “In this latter case, the use of conventional stereo algorithms such as SGM [23] to obtain proxy labels [65, 72], optionally together with confidence measures [64], allowed improving self-supervision from stereo pairs.”
Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching (2017, methodology): “, [11, 26], consists of four steps [24]: 1) matching cost computation; 2) cost aggregation; 3) disparity optimization (derive the disparity from the cost volume); and 4) disparity refinement (post-process the disparity).”
The Utility of Image-Based Point Clouds for Forest Inventory: A Comparison with Airborne Laser Scanning (2013, background): “SGM constrains the possibilities for pixel-wise matching using a cost function, thereby making the matching process markedly more efficient [44].”
A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos (2017, methodology): “For this scenario, we evaluated five methods, [7, 44–46] and a version of SGM stereo [13] on Daisy descriptors [42].”