Hierarchical Discrete Distribution Decomposition for Match Density Estimation
This addresses the computational bottleneck in match density estimation for computer vision applications, offering improved uncertainty estimation and performance, though it is an incremental advancement in probabilistic methods.
The paper tackles the problem of efficiently estimating probabilistic pixel correspondences for optical flow and stereo matching by proposing HD^3, which decomposes match densities hierarchically across scales, achieving state-of-the-art results on established benchmarks.
Explicit representations of the global match distributions of pixel-wise correspondences between pairs of images are desirable for uncertainty estimation and downstream applications. However, the computation of the match density for each pixel may be prohibitively expensive due to the large number of candidates. In this paper, we propose Hierarchical Discrete Distribution Decomposition (HD^3), a framework suitable for learning probabilistic pixel correspondences in both optical flow and stereo matching. We decompose the full match density into multiple scales hierarchically, and estimate the local matching distributions at each scale conditioned on the matching and warping at coarser scales. The local distributions can then be composed together to form the global match density. Despite its simplicity, our probabilistic method achieves state-of-the-art results for both optical flow and stereo matching on established benchmarks. We also find the estimated uncertainty is a good indication of the reliability of the predicted correspondences.