Coarse-to-Fine Lifted MAP Inference in Computer Vision
This work addresses the problem of improving computational efficiency in probabilistic graphical model inference for computer vision applications, though it is incremental as it builds on existing lifted inference and coarse-to-fine methods.
The authors tackled the challenge of applying lifted inference to computer vision problems by proposing a coarse-to-fine template that efficiently handles distinct unary potentials, enabling lifted versions of state-of-the-art algorithms for stereo vision and interactive image segmentation. The result showed that lifted versions had superior anytime performance without loss in final solution quality compared to flat algorithms.
There is a vast body of theoretical research on lifted inference in probabilistic graphical models (PGMs). However, few demonstrations exist where lifting is applied in conjunction with top of the line applied algorithms. We pursue the applicability of lifted inference for computer vision (CV), with the insight that a globally optimal (MAP) labeling will likely have the same label for two symmetric pixels. The success of our approach lies in efficiently handling a distinct unary potential on every node (pixel), typical of CV applications. This allows us to lift the large class of algorithms that model a CV problem via PGM inference. We propose a generic template for coarse-to-fine (C2F) inference in CV, which progressively refines an initial coarsely lifted PGM for varying quality-time trade-offs. We demonstrate the performance of C2F inference by developing lifted versions of two near state-of-the-art CV algorithms for stereo vision and interactive image segmentation. We find that, against flat algorithms, the lifted versions have a much superior anytime performance, without any loss in final solution quality.