We propose a novel method for unsupervised semantic image segmentation based on mutual information maximization between local and global high-level image features.
Ranked #1 on Unsupervised Semantic Segmentation on Potsdam-3 (Pixel Accuracy metric)
We therefore show how we can calculate a normalization based on the expected 3D error, which we can then use to normalize the label jumps in the CRF.
It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models.
The proposed variational network arises naturally from unrolling the iterates of a proximal gradient method applied to a variational energy defined in a joint disparity, color, and confidence image space.
Recent developments established deep learning as an inevitable tool to boost the performance of dense matching and stereo estimation.
Modern optical flow methods are often composed of a cascade of many independent steps or formulated as a black box neural network that is hard to interpret and analyze.
We tackle the computation- and memory-intensive operations on the 4D cost volume by a min-projection which reduces memory complexity from quadratic to linear and binary descriptors for efficient matching.