Multi-Class Model Fitting by Energy Minimization and Mode-Seeking
This addresses the challenge of robustly interpreting complex data with multiple object classes and instances, which is crucial for computer vision applications like 3D reconstruction and motion analysis, representing a strong incremental improvement over existing techniques.
The paper tackles the problem of multi-class multi-instance model fitting, where data contains noisy observations from multiple instances of multiple classes, by proposing Multi-X, a formulation that extends alpha-expansion with a new label-space move and automatic parameter tuning. It significantly outperforms state-of-the-art methods on diverse datasets, including for plane detection, motion segmentation, and geometric fitting tasks.
We propose a general formulation, called Multi-X, for multi-class multi-instance model fitting - the problem of interpreting the input data as a mixture of noisy observations originating from multiple instances of multiple classes. We extend the commonly used alpha-expansion-based technique with a new move in the label space. The move replaces a set of labels with the corresponding density mode in the model parameter domain, thus achieving fast and robust optimization. Key optimization parameters like the bandwidth of the mode seeking are set automatically within the algorithm. Considering that a group of outliers may form spatially coherent structures in the data, we propose a cross-validation-based technique removing statistically insignificant instances. Multi-X outperforms significantly the state-of-the-art on publicly available datasets for diverse problems: multiple plane and rigid motion detection; motion segmentation; simultaneous plane and cylinder fitting; circle and line fitting.