A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration

By Christopher Zach, Thomas Pock, Horst Bischof. 2007

299 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning a Multi-View Stereo Machine (2017, methodology): “These depth maps can then be fused using a variety of different techniques [38, 8, 33, 59, 30].”
OctNetFusion: Learning Depth Fusion from Data (2017, methodology): “Chal(a) TSDF Fusion [9] (b) TV-L1 Fusion [55]”
Hierarchical Surface Prediction for 3D Object Reconstruction (2017, methodology): “The common methods can be broadly grouped as implicit volumetric reconstruction [7], [18], [19], [22], [38] or explicit mesh based [9], [12] approaches.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “signed-distance function (TSDF) [264].”
From Point Clouds to Mesh Using Regression (2017, background): “Ground Truth Point Cloud Our Result Ground Truth Sample Input Image TSDF [7] Poisson [12] TV-L1 [34] Our Method Figure 5.”
Live dense reconstruction with a single moving camera (2010, unknown): “This class of algorithm includes optimal approaches [2, 20 ], though is less amenable to larger scale reconstructions due to prohibitively large memory requirements for the volumetric representation of the global functions.”
Multi-View Stereo: A Tutorial (2015, methodology): “There exist many different techniques that merge multiple depthmaps [52, 76, 94, 142, 153, 207].”
A Symmetry Prior for Convex Variational 3D Reconstruction (2016, methodology): “The depth information is fused into the data cost f : V → R which encodes the depth measurements volumetrically as a truncated signed distance function similar as in [29].”
Class Specific 3D Object Shape Priors Using Surface Normals (2014, methodology): “Approaches penalizing the surface area have been proposed in the discrete optimization literature [12] and also as continuous convex optimization [22].”
Neural RGB-D Surface Reconstruction (2021, background): “In addition, several regularization techniques have been proposed to handle outliers during reconstruction [19, 61, 88].”
Globally optimal bilinear programming for computer vision applications (2008, methodology): “The L1 norm has been used where robustness is a primary concern, such as [30] for range image integration.”
Continuous Global Optimization in Multiview 3D Reconstruction (2007, methodology): “It is related to depth map fusion methods (Curless and Levoy, 1996; Hernández et al., 2007; Zach et al., 2007).”
Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling (2016, methodology): “Our work builds on the convex energy formulation of [17].”
Reconstructing building interiors from images (2009, methodology): “Our depth map integration approach is similar to several existing MVS approaches [13, 25], where they first encode depth map information into a voxel grid covering the”
High Accuracy and Visibility-Consistent Dense Multiview Stereo (2012, unknown): “[70] proposed a globally optimal variational merging of truncated signed distance maps using a volumetric grid.”
Towards Internet-scale multi-view stereo (2010, background): “, by taking weighted combinations of depth samples to recover a mesh [4, 25].”
Deep Marching Cubes: Learning Explicit Surface Representations (2018, methodology): “Towards this goal, many existing approaches formulate 3D reconstruction as inference in a Markov random field [2, 21, 41, 46] or as a variational problem [17, 47].”