Yet Another Cost Aggregation Over Models

摘要

In the recent decades, we have witnessed the advent of local or non-local filters for cost aggregation in stereo matching, pushing the envelope of local methods to the degree of global methods, while maintaining the efficiency. A specific filter with a specific parameter setting may have a potential to best work for an image pair, but may not guarantee equally good performance for other image pairs. To address this problem, we propose a mixture-of-experts model, which applies a heterogeneous set of filters on the cost volume and adaptively combines the results. We employ supervised learning to estimate per-pixel mixing coefficients, which are used to adaptively control the weight of the filter responses. Through experiments, we show that the mixture model significantly reduces errors in disparity estimation and even outperforms the strategy of selecting the best per-pixel filter from the pool of filters in the average sense.