Stereo matching is one of the longest-standing problems in computer vision with close to 40
years of studies and research. Throughout the years the paradigm has shifted from local …

Abstract 3D reconstruction of scenes using multiple images, relying on robust
correspondence search and depth estimation, has been thoroughly studied for the two‐view …

In the stereo matching task, matching cost aggregation is crucial in both traditional methods
and deep neural network models in order to accurately estimate disparities. We propose two …

Stereo matching estimates the disparity between a rectified image pair, which is of great
importance to depth sensing, autonomous driving, and other related tasks. Previous works …

Estimating depth from RGB images is a long-standing ill-posed problem, which has been
explored for decades by the computer vision, graphics, and machine learning communities …

For CNNs based stereo matching methods, cost volumes play an important role in achieving
good matching accuracy. In this paper, we present an end-to-end trainable convolution …

Video deblurring models exploit consecutive frames to remove blurs from camera shakes
and object motions. In order to utilize neighboring sharp patches, typical methods rely …

Recently, records on stereo matching benchmarks are constantly broken by end-to-end
disparity networks. However, the domain adaptation ability of these deep models is quite …

Estimating the depth of the 3D world from 2D images is a classic and important issue in
computer vision, which has been widely studied for decades. With the remarkable effect of …

End-to-end deep networks represent the state of the art for stereo matching. While excelling
on images framing environments similar to the training set, major drops in accuracy occur in …