Disambiguating visual relations using loop constraints

By Christopher Zach, Manfred Klopschitz, Marc Pollefeys. 2010

283 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Computer Vision and Pattern Recognition

Citations in the corpus

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks (2017, methodology): “More recently, higher-order cycle consistency has been used in structure from motion [56], 3D shape matching [19], co-segmentation [51], dense semantic alignment [59, 60], and depth estimation [12].”
Temporal Cycle-Consistency Learning (2019, methodology): “It has been applied successfully for tasks like co-segmentation [43, 44], structure from motion [49, 51], and image matching [54, 55, 56].”
Unsupervised Visual Representation Learning by Graph-Based Consistent Constraints (2016, methodology): “Cycle consistency in a graph has been applied to various computer vision and graphics problems, including co-segmentation [28,29], structure from motion [30,31] and image matching [32,33].”
Dense Semantic 3D Reconstruction (2017, background): “Camera poses where obtained with the publicly available structure from motion pipeline [42].”
FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences (2015, background): “The concept of cycle consistency has also been explored in joint shape matching [17, 32], co-segmentation [40, 41] as well as SfM [47, 42].”
Multi-Label Semantic 3D Reconstruction Using Voxel Blocks (2016, methodology): “We obtained the camera poses using a publicly available structure from motion pipeline [29], and the depth maps are obtained using the publicly available plane sweep stereo matching implementation [9] with zero mean normalized cross correlation and subsequent semiglobal matching on the cost volume [”
Class Specific 3D Object Shape Priors Using Surface Normals (2014, methodology): “As a first step the camera poses are computed using the publicly available structure from motion software [21].”
A Survey on Structure from Motion (2017, methodology): “More concretely, [88] considers the underlying graph of related images (having edges endowed with the pairwise transformations) and proposes to detect inconsistent edges using the fact that (in the noiseless case) chaining all pairwise transformations along any cycle must result in the identity…”
Segment based 3D object shape priors (2015, methodology): “The camera poses are obtained by using the publicly available structure from motion software [27].”
Joint 3D Scene Reconstruction and Class Segmentation (2013, background): “Camera poses where obtained with the publicly available structure from motion pipeline [26].”
Image Co-segmentation via Consistent Functional Maps (2013, background): “The cycle-consistency constraint has been applied in the vision community for obtaining consistent affine matches among multiple images [25, 17].”