Learning for Multi-Model and Multi-Type Fitting
This addresses the multi-model multi-type fitting problem in computer vision, offering a novel solution for tasks like geometric model fitting, but it appears incremental as it builds on existing clustering and embedding ideas.
The paper tackles the problem of simultaneously fitting multiple types and numbers of models to data, which is challenging due to issues like sampling imbalance and parameter tuning. It proposes a deep feature embedding method that makes clustering easier, achieving state-of-the-art results on synthetic and real-world datasets.
Multi-model fitting has been extensively studied from the random sampling and clustering perspectives. Most assume that only a single type/class of model is present and their generalizations to fitting multiple types of models/structures simultaneously are non-trivial. The inherent challenges include choice of types and numbers of models, sampling imbalance and parameter tuning, all of which render conventional approaches ineffective. In this work, we formulate the multi-model multi-type fitting problem as one of learning deep feature embedding that is clustering-friendly. In other words, points of the same clusters are embedded closer together through the network. For inference, we apply K-means to cluster the data in the embedded feature space and model selection is enabled by analyzing the K-means residuals. Experiments are carried out on both synthetic and real world multi-type fitting datasets, producing state-of-the-art results. Comparisons are also made on single-type multi-model fitting tasks with promising results as well.