Bayesian Model Estimation and Selection for Epipolar Geometry and Generic Manifold Fitting

By Philip H. S. Torr. International Journal of Computer Vision, 2002

299 citations recorded by the source corpus.

How researchers see this paper

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

The dual-bootstrap iterative closest point algorithm with application to retinal image registration (2003, methodology): “(See [77] for a similar approach in the context of multi-camera imaging geometry.”
Performance Evaluation of RANSAC Family (2009, methodology): “MAPSAC (Maximum A Posterior Estimation SAC) [28] follows Bayesian approach in contrast to MLESAC, but its loss function is similar with MSAC and MLESAC since it assumes uniform prior. pbM-estimator (Projection-based Mestimator) [25] attempted non-parametric approach in contrast to the parametric err”
MAGSAC: Marginalizing Sample Consensus (2018, methodology): “For RANSAC, QRANSAC(θ, σ,P) = |I(θ, σ,P)| and for MSAC, it is QMSAC(θ, σ,P) = |I(θ,σ,P)|∑ i=1 ( 1− D 2(θ, Ii(θ, σ,P)) 9/4σ2 ) , where Ii(θ, σ,P) is the ith inlier.”
Coarse-to-fine low-rank structure-from-motion (2008, background): “The second reason is that model selection criteria such as AIC , BIC or GRIC are based on a particular distribution of the residuals, namely a possibly ro-bustiﬁed gaussian distribution, see [8, 10].”
MAGSAC++, a Fast, Reliable and Accurate Robust Estimator (2019, methodology): “In MAPSAC [26], the robust estimation is formulated as a process that esti- mates both the parameters of the data distribution and the quality of the model in terms of maximum a posteriori.”