Energy-Based Geometric Multi-model Fitting

By Hossam N. Isack, Yuri Boykov. International Journal of Computer Vision, 2012

357 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/1195c6401ec86cec7bc773485d4ac61b3787be09

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

In Environmental Engineering

Citations in the corpus

Video Pop-up: Monocular 3D Reconstruction of Dynamic Scenes (2014, methodology): “The assignment of tracks to models and the estimation of model parameters is then optimised jointly [18], [31] to minimise a geometric cost subject to the constraint that neighbouring tracks must belong to the same model.”
State of research in automatic as-built modelling (2015, background): “point cloud modelling, the works on geometric multi-model fitting proposed in [62,119] are relevant for as-built modelling.”
MAGSAC: Marginalizing Sample Consensus (2018, methodology): “motion segmentation [25], short baseline stereo [25, 27], wide baseline stereo matching [18, 13, 14], detection of geometric primitives [21], image mosaicing [7], and to perform [28] or initialize multi-model fitting [10, 17].”
MAGSAC++, a Fast, Reliable and Accurate Robust Estimator (2019, unknown): “, motion segmentation [27], short baseline stereo [27, 29], wide baseline matching [19, 14, 15], detection of geometric primitives [23], image mosaicing [7], and to perform [32] or initialize multi-model fitting [9, 18].”
Discrete-continuous optimization for multi-target tracking (2012, methodology): “While optimization with label costs is challenging due to the fact that they are global terms, it can be approached using the integrated energy minimization framework of [9, 12].”
Graph-Cut RANSAC (2017, methodology): “PEARL [12] introduced pair-wise energy to geometric model fitting.”
Conditional Object-Centric Learning from Video (2021, methodology): “These methods use motion information at test time to, for example, cluster trajectories in order to segment independently moving objects (Faktor & Irani, 2014) or estimate multiple fundamental matrices between two views (Isack & Boykov, 2012), to name a few.”
Fast Approximate Energy Minimization with Label Costs (2010, methodology): “For simplicity, we will discuss PEARL in the context of geometric model fitting, as in [31].”
RAPter (2015, methodology): “In a more general data analysis context, the PEARL setup [Isack and Boykov 2012] formulated model-fitting as a labeling problem using a global energy formulation.”