In computer vision, edge and object contour detection is essential for higher-level vision
tasks, such as shape matching, visual salience, image segmentation, and object recognition …

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 Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in
matching tasks. However, all-pairs correlations lack non-local geometry knowledge and …

We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical
flow network RAFT [35]. We introduce multi-level convolutional GRUs, which more efficiently …

This paper presents HITNet, a novel neural network architecture for real-time stereo
matching. Contrary to many recent neural network approaches that operate on a full …

Monocular depth estimators can be trained with various forms of self-supervision from
binocular-stereo data to circumvent the need for high-quality laser-scans or other ground …

State-of-the-art stereo matching networks have difficulties in generalizing to new unseen
environments due to significant domain differences, such as color, illumination, contrast, and …

Deep learning-based stereo matching methods have made remarkable progress in recent
years. However, it is still a challenging task to achieve high accuracy in real time. In …

Great progress has been made on estimating disparity maps from stereo images. However,
with the limited stereo data available in the existing datasets and unstable ranging precision …

Real-time performance of stereo matching networks is important for many applications, such
as automatic driving, robot navigation and augmented reality (AR). Although significant …