Continuous Markov Random Fields for Robust Stereo Estimation
This work addresses the problem of accurate and efficient stereo depth estimation for computer vision applications, representing an incremental improvement over existing slanted plane MRF-based methods.
The paper tackles robust stereo estimation by introducing a novel slanted-plane MRF model that jointly reasons about occlusion boundaries and depth, outperforming state-of-the-art methods on Middlebury and KITTI datasets with an average inference time of 2 minutes on high-resolution imagery.
In this paper we present a novel slanted-plane MRF model which reasons jointly about occlusion boundaries as well as depth. We formulate the problem as the one of inference in a hybrid MRF composed of both continuous (i.e., slanted 3D planes) and discrete (i.e., occlusion boundaries) random variables. This allows us to define potentials encoding the ownership of the pixels that compose the boundary between segments, as well as potentials encoding which junctions are physically possible. Our approach outperforms the state-of-the-art on Middlebury high resolution imagery as well as in the more challenging KITTI dataset, while being more efficient than existing slanted plane MRF-based methods, taking on average 2 minutes to perform inference on high resolution imagery.