Energy Based Multi-Model Fitting and Matching Problems

Feature matching and model fitting are fundamental problems in multi-view geometry. They are chicken-&-egg problems: if models are known it is easier to find matches and vice versa. Standard multi-view geometry techniques sequentially solve feature matching and model fitting as two independent problems after making fairly restrictive assumptions. For example, matching methods rely on strong discriminative power of feature descriptors, which fail for stereo images with repetitive textures or wide baseline. Also, model fitting methods assume given feature matches, which are not known a priori. Moreover, when data supports multiple models the fitting problem becomes challenging even with known matches and current methods commonly use heuristics. One of the main contributions of this thesis is a joint formulation of fitting and matching problems. We are first to introduce an objective function combining both matching and multi-model estimation. We also propose an approximation algorithm for the corresponding NP-hard optimization problem using block-coordinate descent with respect to matching and model fitting variables. For fixed models, our method uses min-cost-max-flow based algorithm to solve a generalization of a linear assignment problem with label cost (sparsity constraint). Fixed matching case reduces to multi-model fitting subproblem, which is interesting in its own right. In contrast to standard heuristic approaches, we introduce global objective functions for multi-model fitting using various forms of regularization (spatial smoothness and sparsity) and propose a graph-cut based optimization algorithm, PEaRL. Experimental results show that our proposed mathematical formulations and optimization algorithms improve the accuracy and robustness of model estimation over the state-of-the-art in computer vision