Multi-view reconstruction preserving weakly-supported surfaces

By Michal Jancosek, Tomás Pajdla. 2011

404 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Geology

How researchers see this paper

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

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Geology

Citations in the corpus

SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis (2017, background): “Other approaches have focused on more advanced depth fusion algorithms [13].”
Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling (2016, background): “The idea was extended by [20], who focus on visibility to also recover weakly supported objects.”
Range sensor and silhouette fusion for high-quality 3D Scanning (2015, background): “In particular, multiview stereo approaches currently obtain state-of-the-art results in reconstruction purely from multiple calibrated RGB images [12], [6], [13], [16], [21].”
Learning Where to Classify in Multi-view Semantic Segmentation (2014, methodology): “The final surface is recovered using a robust volumetric graph cuts optimization [45].”
Joint 3D Scene Reconstruction and Class Segmentation (2013, methodology): “[9] proposes to extend an adaptive volumetric method for surface reconstruction in order not to miss important parts of the scene in the final geometry.”
A comprehensive survey of augmented reality assembly research (2016, background): “With these scene capture technologies, dense 3D reconstruction [161] can be achieved, which can facilitate virtual objects to interact with the real assembly workspace.”
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction (2020, methodology): “functions using, for example, kernel-based techniques [7,27,48,16]. Visibility or free space methods estimate which subset of 3D space is occupied, often by subdividing space into distinct tetrahedra [31,26,3]. These methods aim to solve for a globally view consistent surface representation. 4 Chabr”
Massively Parallel Multiview Stereopsis by Surface Normal Diffusion (2015, methodology): “We see surface fitting as a subsequent step that is largely independent of the matching – in fact the most popular approaches [21, 25, 28] are rather agnostic about the preceding matcher, and we found the widely used Poisson method [25] to work well for our point clouds.”
Dense Semantic 3D Reconstruction (2017, methodology): “Jancosek and Pajdla [16] proposes to extend an adaptive volumetric method for surface reconstruction in order not to miss important parts of the scene in the final geometry.”
A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos (2017, methodology): “PMVS and Gipuma produce very incomplete and noisy results while CMPMVS fails completely.”
Generalized Connectivity Constraints for Spatio-temporal 3D Reconstruction (2014, methodology): “Approximate silhouette information was used for all methods except of the method by Jancosek and Pajdla [17] for which it cannot be used.”
3D all the way: Semantic segmentation of urban scenes from start to end in 3D (2015, methodology): “7x subsampling the original, ‘High-res’ mesh produced by the CMPMVS algorithm [17] in 270 minutes.”
Pixelwise View Selection for Unstructured Multi-View Stereo (2016, methodology): “Jancoseck and Pajdla [28] fuses multiple depth estimates into a surface and, by evaluating visibility in 3D space, they also attempt to reconstruct parts that are not directly supported by depth measurements.”
Free View Synthesis (2020, methodology): “We utilize a Delaunaybased reconstruction [18,23] as it can tolerate a certain amount of outliers.”
Multi-View Stereo: A Tutorial (2015, methodology): “More recently, an SfM software “VisualSFM” by Changchang Wu [198], which is a GUI application for SfM, and an MVS software “CMPMVS” by Michal Jancosek and Tomas Pajdla [109] were developed as compelling alternatives.”
Structure from Motion (SfM) Photogrammetry with Drone Data: A Low Cost Method for Monitoring Greenhouse Gas Emissions from Forests in Developing Countries (2017, methodology): “5 (Michal Jancosek, Prague, Czech Republic) [49] for the SfM/MVS process) was used to process the data.”